# Loopmaster llms-full.txt

Generated deterministically from repo artifacts during the site build. Do not edit by hand.

## Site fetch contract

- Agent entry point: https://loopmaster-ai.pages.dev/llms.txt
- Full context: https://loopmaster-ai.pages.dev/llms-full.txt
- Registry JSON: https://loopmaster-ai.pages.dev/registry/index.json
- Skill catalog: https://loopmaster-ai.pages.dev/skills/index.json
- Agent guide: https://loopmaster-ai.pages.dev/agent-guide
- Spec page: https://loopmaster-ai.pages.dev/spec

An agent with only the site URL can reach a template manifest in three fetches:
1. https://loopmaster-ai.pages.dev/llms.txt
2. https://loopmaster-ai.pages.dev/registry/index.json
3. https://loopmaster-ai.pages.dev/templates/research-watch/loop.yaml

## BEGIN llms.txt

# Loopmaster

Loopmaster is a repository of agent-readable loop workflow templates: recurring AI work patterns that can be discovered, installed, verified, and maintained from checked-in manifests and docs.

Usage contract for agents:
- To create a new loop from a manual workflow, fetch `skills/authoring/loopify/SKILL.md` or the public `/skills/loopify/SKILL.md`, start with its Q&A intake, ask only for missing details, and do not schedule, publish, spend, request credential values, or make destructive changes until the human approves.
- Treat `https://loopmaster-ai.pages.dev/registry/index.json` as the structured catalog and generated source of truth for available loop templates, self-maintenance loops, skill packs, and verification status.
- Before installing a loop, read that template's `loop.yaml` and `AGENT-INSTALL.md` exactly; the manifest defines what is allowed, required, verified, and human-gated, while the install doc maps the manifest to concrete commands.
- Do not claim a template is verified unless the registry entry says so and the evidence link is still current. Draft or unverified entries may be explored, but not represented as proven installs.
- Respect every `permissions`, `human_gates`, and `failure_policy` field. Escalate instead of guessing when a gate fires, credentials are missing, or verification fails.
- Never read or expose credentials beyond the scopes declared by the manifest and install guide.

Fast fetch path from only the site URL:
1. Fetch this file: `https://loopmaster-ai.pages.dev/llms.txt`.
2. Fetch the catalog: `https://loopmaster-ai.pages.dev/registry/index.json`.
3. Pick a template and fetch its `manifest_path`, for example `https://loopmaster-ai.pages.dev/templates/research-watch/loop.yaml`.

Primary site artifacts:
- Catalog: `https://loopmaster-ai.pages.dev/registry/index.json`
- Loop spec: `https://loopmaster-ai.pages.dev/spec`
- JSON Schema: `https://loopmaster-ai.pages.dev/spec/loop.schema.json`
- Template directories: `https://loopmaster-ai.pages.dev/loops`
- Self-maintenance loops: `https://loopmaster-ai.pages.dev/loops`
- Skill packs: `https://loopmaster-ai.pages.dev/skills`
- Resource library: `https://loopmaster-ai.pages.dev/resources`
- Resource rubric: `https://loopmaster-ai.pages.dev/resources/rubric`
- Agent guide: `https://loopmaster-ai.pages.dev/agent-guide`

Current first-template path:
- `https://loopmaster-ai.pages.dev/templates/research-watch/loop.yaml`
- `https://loopmaster-ai.pages.dev/templates/research-watch/AGENT-INSTALL.md`
- `https://loopmaster-ai.pages.dev/templates/research-watch/README.md`

Public-site paths:
- `/llms.txt`
- `/llms-full.txt`
- `/registry/index.json`
- `/agent-guide`
- `/spec`
- `/loops`
- `/skills`
- `/resources`

All repo-relative artifact paths exposed here are also served under https://loopmaster-ai.pages.dev/. Prefer the site URLs when starting from the public site.

Quickstart for agents: https://loopmaster-ai.pages.dev/quickstart
Skill catalog: https://loopmaster-ai.pages.dev/skills/index.json
Per-skill instructions: https://loopmaster-ai.pages.dev/skills/<id>/SKILL.md

Expanded context: https://loopmaster-ai.pages.dev/llms-full.txt

Three-fetch site proof:
1. GET https://loopmaster-ai.pages.dev/llms.txt
2. GET https://loopmaster-ai.pages.dev/registry/index.json
3. GET https://loopmaster-ai.pages.dev/templates/research-watch/loop.yaml

## END llms.txt

## BEGIN spec/loop-spec-v0.1.md

# Loopmaster `loop.yaml` Specification v0.1

Status: draft

This document defines the draft v0.1 Loopmaster loop manifest format. It is descriptive and backend-agnostic: a manifest declares what a loop needs, may do, must verify, and when it must escalate; backend-specific install instructions live in adjacent docs and in the `backends` hint section.

v0.1 remains draft until LM-RETRO-01. Template authors MAY propose changes while the first Phase 0 templates are being written. Consumers MUST NOT treat v0.1 as frozen until the retro explicitly freezes it.

## 1. Conformance language

The key words MUST, MUST NOT, REQUIRED, SHOULD, SHOULD NOT, MAY, and OPTIONAL are to be interpreted as normative requirements for v0.1 manifests.

A conforming manifest:

- MUST be named `loop.yaml` for templates, or `<id>.loop.yaml` for Loopmaster's own maintenance loops.
- MUST validate against `spec/loop.schema.json`.
- MUST set `spec_version` to the string `"0.1"`.
- MUST NOT include unknown top-level keys.
- MUST include at least one permission in `permissions.allowed_actions`.
- SHOULD keep field values short enough for an agent to read the whole manifest in one context window.
- SHOULD keep prose documentation and manifest fields consistent: every operational claim in prose should map to a manifest field, and every manifest field should be explained by the human or agent install docs.

## 2. Manifest shape

Top-level fields are deliberately small and stable. Optional fields are omitted when they do not add useful installation or safety information.

| Field | Type | Required | Example | Definition |
|---|---|---:|---|---|
| `spec_version` | string | yes | `"0.1"` | Manifest spec version. v0.1 manifests MUST use the exact string `"0.1"`. |
| `id` | string | yes | `research-watch` | Stable kebab-case identifier. It SHOULD match the template directory name. |
| `name` | string | yes | `Research Watch Loop` | Human-readable display name. |
| `purpose` | string | yes | `Monitor sources and turn high-signal changes into cited findings or tasks.` | One-sentence description of the loop's job and outcome. |
| `audience` | array of enum strings | yes | `[human, agent]` | Primary consumers. Allowed values: `human`, `agent`, `operator`, `team`. |
| `trigger` | object | yes | `{type: schedule, default: daily}` | What starts the loop. See §3. |
| `inputs` | object | no | `{sources: [{type: rss}]}` | External sources, files, or environment variables the loop reads. See §4. |
| `capabilities` | array of strings | no | `[polling, source_summarization, task_creation]` | Runtime or agent-harness capabilities needed to execute the loop. |
| `permissions` | object | yes | `{allowed_actions: [read_web, write_report]}` | Actions the loop may and may not take. See §5. |
| `state` | object | yes | `{paths: [.loopmaster/state/research-watch.json]}` | Durable state paths used for dedupe, memory, progress, or audit correlation. |
| `outputs` | object | yes | `{artifacts: [docs/research/YYYY-MM-DD-findings.md]}` | Files, notifications, or tasks the loop emits. |
| `verification` | object | yes | `{required: [every finding has a source URL], commands: [{run: python3 tools/check.py}]}` | Declarative success criteria plus executable checks. |
| `human_gates` | object | yes | `{required_for: [public publishing]}` | Conditions that require a human or reviewer before acting. |
| `failure_policy` | object | yes | `{retry: 2, escalate_after: repeated_provider_failure}` | Retry, escalation, and rollback behavior. |
| `maintenance` | object | yes | `{freshness_cadence: weekly}` | How often the template or loop should be reviewed for rot. |
| `backends` | object | yes | `{cron: {schedule: daily}}` | Runtime-specific install hints for supported backends. |

## 3. `trigger`

`trigger` declares what starts the loop. It is a contract, not the scheduler implementation.

| Field | Type | Required | Example | Definition |
|---|---|---:|---|---|
| `trigger.type` | enum string | yes | `schedule` | One of `schedule`, `webhook`, `manual`, `user_goal`, `ci_event`, `issue_event`, `feed_change`. |
| `trigger.default` | string | no | `daily` | Human-readable default cadence or starter condition. |
| `trigger.schedule` | string | no | `0 9 * * 1` | Concrete schedule hint when the trigger is schedule-like. |
| `trigger.event` | string | no | `pull_request.failed_check` | Event name when the trigger is event-like. |

## 4. `inputs`

`inputs` is OPTIONAL because some loops operate only on local state or a user goal. When present, it MUST contain at least one of the fields below.

| Field | Type | Required | Example | Definition |
|---|---|---:|---|---|
| `inputs.sources` | array of source objects | no | `[{type: web_search, query: agent loop engineering}]` | External or internal systems the loop reads. |
| `inputs.environment_variables` | array of strings | no | `[GITHUB_TOKEN]` | Environment variable names required by the loop. Values MUST NOT appear in the manifest. |
| `inputs.files` | array of strings | no | `[resources/SOURCES.md]` | Repo-relative or documented runtime paths the loop reads. |

Source object fields:

| Field | Type | Required | Example | Definition |
|---|---|---:|---|---|
| `type` | enum string | yes | `rss` | One of `rss`, `web_search`, `github_repo`, `url`, `file`, `api`, `database`, `kanban`, `calendar`. |
| `name` | string | no | `Anthropic engineering blog` | Human-readable source label. |
| `url` | string | no | `https://www.anthropic.com/engineering` | Source URL. |
| `query` | string | no | `agent loop engineering` | Search query or API query. |
| `path` | string | no | `docs/research/loop-landscape.md` | File or state path. |

## 5. `permissions`

`permissions` is REQUIRED because safety is part of the product. Empty permissions are invalid.

| Field | Type | Required | Example | Definition |
|---|---|---:|---|---|
| `permissions.allowed_actions` | array of strings | yes | `[read_web, write_report, create_task]` | Actions the loop may perform autonomously. MUST contain at least one item. |
| `permissions.forbidden_actions` | array of strings | no | `[publish_publicly_without_approval, spend_money]` | Actions the loop MUST NOT perform autonomously. |
| `permissions.credential_scopes` | array of strings | no | `[read:repo, issues:write]` | Credential scopes needed. Names only; never include secret values. |

## 6. `state`

`state` is REQUIRED so loops can dedupe, resume, and produce an audit trail.

| Field | Type | Required | Example | Definition |
|---|---|---:|---|---|
| `state.paths` | array of strings | yes | `[.loopmaster/state/research-watch.json]` | Files or stores where durable loop state is written. |
| `state.retention` | string | no | `90 days` | How long state should be kept before pruning or archiving. |

## 7. `outputs`

`outputs` is REQUIRED and MUST contain at least one output category.

| Field | Type | Required | Example | Definition |
|---|---|---:|---|---|
| `outputs.artifacts` | array of strings | no | `[docs/research/YYYY-MM-DD-findings.md]` | Files or structured artifacts the loop writes. |
| `outputs.notifications` | array of strings | no | `[summary]` | Notifications the loop may send. |
| `outputs.tasks` | array of strings | no | `[kanban_card_for_high_signal_finding]` | Task or issue outputs the loop may create. |

## 8. `verification`

`verification` is REQUIRED. It combines human-readable assertions with commands that agents and CI can execute.

| Field | Type | Required | Example | Definition |
|---|---|---:|---|---|
| `verification.required` | array of strings | yes | `[every finding has a source URL]` | Declarative acceptance criteria. |
| `verification.commands` | array of command objects | yes | `[{name: validate findings, run: python3 tools/check_findings.py}]` | Executable checks. MUST contain at least one command. |

Command object fields:

| Field | Type | Required | Example | Definition |
|---|---|---:|---|---|
| `name` | string | no | `validate findings` | Human-readable check name. |
| `run` | string | yes | `python3 tools/check_findings.py` | Command to execute from the documented working directory. |
| `expected` | string | no | `exits 0 and prints OK` | Expected success signal. |

## 9. `human_gates`

`human_gates` is REQUIRED. A loop that appears to need no approval SHOULD still declare the boundary that would make it unsafe.

| Field | Type | Required | Example | Definition |
|---|---|---:|---|---|
| `human_gates.required_for` | array of strings | yes | `[public publishing, credential changes]` | Conditions that MUST stop for human or reviewer approval. |
| `human_gates.approver` | string | no | `maintainer` | Role or person expected to approve gated actions. |

## 10. `failure_policy`

`failure_policy` is REQUIRED so agents know when to retry and when to stop.

| Field | Type | Required | Example | Definition |
|---|---|---:|---|---|
| `failure_policy.retry` | integer | yes | `2` | Maximum retry attempts before escalation. |
| `failure_policy.escalate_after` | string | yes | `repeated_provider_failure` | Condition or class of failure that triggers escalation. |
| `failure_policy.rollback` | string | no | `revert the proposal branch and leave the previous state file unchanged` | Rollback or recovery guidance. |

## 11. `maintenance`

`maintenance` is REQUIRED because loop rot is an expected failure mode.

| Field | Type | Required | Example | Definition |
|---|---|---:|---|---|
| `maintenance.freshness_cadence` | string | yes | `weekly` | How often to review this loop/template for source, API, model, or process drift. |
| `maintenance.owner` | string | no | `Loopmaster maintainers` | Owner responsible for maintenance. |
| `maintenance.audit_log` | string | no | `loops/log/` | Where maintenance evidence is recorded. |

## 12. `backends`

`backends` is REQUIRED and MUST contain at least one supported backend hint. Hints are not executable adapters; they tell an installer where the manifest maps onto runtime-specific setup.

Allowed backend keys in v0.1 are `cron`, `github_actions`, and `agent_kanban`.

| Field | Type | Required | Example | Definition |
|---|---|---:|---|---|
| `backends.cron` | backend hint object | no | `{schedule: daily}` | Installation hints for cron-like schedulers. |
| `backends.github_actions` | backend hint object | no | `{workflow: .github/workflows/research-watch.yml}` | Installation hints for GitHub Actions. |
| `backends.agent_kanban` | backend hint object | no | `{task_template: Create a weekly research watch task}` | Installation hints for agent task boards such as Hermes kanban. |

Backend hint fields:

| Field | Type | Required | Example | Definition |
|---|---|---:|---|---|
| `schedule` | string | no | `daily` | Cadence or cron expression. |
| `workflow` | string | no | `.github/workflows/research-watch.yml` | Workflow file or runtime entry point. |
| `task_template` | string | no | `Create a weekly research-watch task assigned to researcher` | Task prompt or template hint. |
| `install_notes` | array of strings | no | `[Run from repo root]` | Backend-specific setup notes. |

## 13. Worked example

This example updates the R1 §7 research-watch manifest to v0.1. It is intentionally still a draft template shape, but it validates against `spec/loop.schema.json`.

```yaml
spec_version: "0.1"
id: research-watch
name: Research Watch Loop
purpose: Monitor sources and turn high-signal changes into cited findings or tasks.
audience: [human, agent]
trigger:
  type: schedule
  default: daily
  schedule: "0 9 * * *"
inputs:
  sources:
    - type: rss
      name: practitioner blogs
    - type: web_search
      query: agent loop engineering
    - type: github_repo
      url: https://github.com/anthropics/claude-cookbooks
capabilities:
  - polling
  - source_summarization
  - dedupe
  - task_creation
permissions:
  allowed_actions:
    - read_web
    - write_report
    - create_task
  forbidden_actions:
    - publish_publicly_without_approval
    - spend_money
    - delete_user_data
  credential_scopes:
    - web:read
    - kanban:create
state:
  paths:
    - .loopmaster/state/research-watch.json
  retention: 90 days
outputs:
  artifacts:
    - docs/research/YYYY-MM-DD-findings.md
  notifications:
    - summary
  tasks:
    - kanban_card_for_high_signal_finding
verification:
  required:
    - every finding has a source URL
    - no duplicate finding from previous state
    - recommendations include confidence/risk
  commands:
    - name: validate findings report
      run: python3 tools/validate_findings.py docs/research/YYYY-MM-DD-findings.md
      expected: exits 0 and prints OK
human_gates:
  required_for:
    - public publishing
    - product direction changes
    - credential changes
  approver: maintainer
failure_policy:
  retry: 2
  escalate_after: repeated_provider_failure
  rollback: leave prior state file unchanged and report partial findings only
maintenance:
  freshness_cadence: weekly
  owner: Loopmaster maintainers
  audit_log: loops/log/
backends:
  cron:
    schedule: daily
    install_notes:
      - Run from the repository root.
  github_actions:
    workflow: .github/workflows/research-watch.yml
  agent_kanban:
    task_template: Create a weekly research-watch task assigned to researcher.
```

## 14. Versioning notes

v0.1 is expected to change while the Phase 0 templates exercise it. Backward-incompatible changes SHOULD be recorded in `spec/CHANGELOG.md`. Unknown `spec_version` values MUST be rejected by v0.1 validators.

## END spec/loop-spec-v0.1.md

## BEGIN registry/index.json

{
  "f2_skills": {
    "count": 2,
    "skill_packs": [
      "loopify",
      "deploy-your-first-loop"
    ]
  },
  "sample": false,
  "schema_version": "lm-reg-01",
  "skills": [
    {
      "backends": [
        "cron",
        "github_actions",
        "agent_kanban"
      ],
      "category": "authoring",
      "deploys_template": null,
      "description": "Use when a human describes a manual workflow and needs Q&A intake plus a draft Loopmaster loop bundle: loop.yaml, README, AGENT-INSTALL.md, verify.sh, and registry-entry instructions.",
      "group": "authoring",
      "id": "loopify",
      "name": "Loopify",
      "path": "skills/authoring/loopify/SKILL.md",
      "requirements": [
        "repository checkout containing spec/loop.schema.json",
        "free-text workflow description or notes from the human operator",
        "optional artifacts such as scripts, checklists, sample inputs, or previous cron entries",
        "uv with pyyaml and jsonschema, or check-jsonschema with pyyaml, for manifest validation",
        "shell access for deterministic verify.sh dry-runs"
      ],
      "url": "https://loopmaster-ai.pages.dev/skills/loopify/SKILL.md",
      "verification": {
        "details": "no verification evidence found under verification/",
        "status": "unverified"
      }
    },
    {
      "backends": [
        "cron",
        "github_actions",
        "agent_kanban"
      ],
      "category": "authoring",
      "deploys_template": "research-watch",
      "description": "Use when an agent or human wants to deploy the research-watch Loopmaster template through cron, GitHub Actions, or agent-kanban and verify a running loop in one session.",
      "group": "getting-started",
      "id": "deploy-your-first-loop",
      "name": "Deploy Your First Loop",
      "path": "skills/getting-started/deploy-your-first-loop/SKILL.md",
      "requirements": [
        "Python 3",
        "repository checkout containing templates/research-watch",
        "uv for manifest validation",
        "cron for the local scheduler backend, or GitHub Actions / Hermes kanban for alternate backends",
        "no web-search API key for the default research-watch run"
      ],
      "url": "https://loopmaster-ai.pages.dev/skills/deploy-your-first-loop/SKILL.md",
      "verification": {
        "date": "2026-07-07",
        "details": "positive dated skill verification evidence found",
        "evidence_path": "skills/getting-started/deploy-your-first-loop/verification/cron-scratch-transcript.md",
        "evidence_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/skills/getting-started/deploy-your-first-loop/verification/cron-scratch-transcript.md",
        "status": "verified"
      }
    }
  ],
  "templates": [
    {
      "backends": [
        "agent_kanban",
        "cron",
        "github_actions"
      ],
      "doc_path": "templates/agent-usability-test/README.md",
      "doc_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/agent-usability-test/README.md",
      "id": "agent-usability-test",
      "install_path": "templates/agent-usability-test/AGENT-INSTALL.md",
      "install_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/agent-usability-test/AGENT-INSTALL.md",
      "manifest_path": "templates/agent-usability-test/loop.yaml",
      "manifest_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/agent-usability-test/loop.yaml",
      "name": "Agent Usability Test Loop",
      "permissions": {
        "allowed_actions": [
          "read_repo",
          "create_clean_checkout",
          "run_documented_commands",
          "write_transcript",
          "write_friction_report",
          "create_followup_task"
        ],
        "credential_scopes": [
          "repo:read",
          "kanban:create"
        ],
        "forbidden_actions": [
          "use_unlisted_project_context",
          "read_private_credentials",
          "mutate_source_repository_without_approval",
          "claim_verified_without_evidence",
          "publish_public_verified_badge_without_approval"
        ],
        "summary": "6 allowed action(s), 5 forbidden action(s), 2 credential scope(s)"
      },
      "purpose": "Run a clean-room agent through template or site docs and turn transcript evidence into a pass/fail friction report.",
      "spec_version": "0.1",
      "trigger": {
        "default": "before claiming agent-install compatibility or after major template/site doc changes",
        "type": "manual"
      },
      "triggers": [
        "manual",
        "before claiming agent-install compatibility or after major template/site doc changes"
      ],
      "verification": {
        "age_days": 0,
        "date": "2026-07-07",
        "details": "positive dated evidence found",
        "evidence_path": "templates/agent-usability-test/verification/dry-run-checklist.md",
        "evidence_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/agent-usability-test/verification/dry-run-checklist.md",
        "rule": "positive verification evidence auto-stales after 30 days",
        "stale_after": "2026-08-06",
        "status": "verified"
      }
    },
    {
      "backends": [
        "agent_kanban",
        "cron",
        "github_actions"
      ],
      "doc_path": "templates/ci-repair/README.md",
      "doc_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/ci-repair/README.md",
      "id": "ci-repair",
      "install_path": "templates/ci-repair/AGENT-INSTALL.md",
      "install_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/ci-repair/AGENT-INSTALL.md",
      "manifest_path": "templates/ci-repair/loop.yaml",
      "manifest_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/ci-repair/loop.yaml",
      "name": "CI Repair Loop",
      "permissions": {
        "allowed_actions": [
          "read_ci_status",
          "read_ci_logs",
          "read_repository_files",
          "run_local_tests",
          "modify_test_code",
          "propose_non_test_code_patch",
          "push_repair_branch",
          "open_pull_request",
          "create_follow_up_task"
        ],
        "credential_scopes": [
          "repo:contents:write",
          "pull_request:write",
          "actions:read",
          "checks:read",
          "kanban:create"
        ],
        "forbidden_actions": [
          "disable_required_checks_without_approval",
          "weaken_assertions_without_root_cause_evidence",
          "delete_failing_tests_to_make_ci_green",
          "mask_errors_with_blanket_retries_or_ignores",
          "merge_non_test_code_without_human_diff_review",
          "expose_credentials_in_logs_or_comments"
        ],
        "summary": "9 allowed action(s), 6 forbidden action(s), 5 credential scope(s)"
      },
      "purpose": "Detect a failing CI signal, inspect the failure evidence, make the smallest justified patch, rerun verification, and open or update a pull request without masking the real issue.",
      "spec_version": "0.1",
      "trigger": {
        "default": "failing pull request or protected-branch check",
        "event": "check_suite_failure",
        "type": "ci_event"
      },
      "triggers": [
        "ci_event",
        "failing pull request or protected-branch check",
        "check_suite_failure"
      ],
      "verification": {
        "age_days": 0,
        "date": "2026-07-07",
        "details": "positive dated evidence found",
        "evidence_path": "templates/ci-repair/verification/dry-read-ambiguity-checklist.md",
        "evidence_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/ci-repair/verification/dry-read-ambiguity-checklist.md",
        "rule": "positive verification evidence auto-stales after 30 days",
        "stale_after": "2026-08-06",
        "status": "verified"
      }
    },
    {
      "backends": [
        "agent_kanban",
        "cron",
        "github_actions"
      ],
      "doc_path": "templates/content-freshness/README.md",
      "doc_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/content-freshness/README.md",
      "id": "content-freshness",
      "install_path": "templates/content-freshness/AGENT-INSTALL.md",
      "install_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/content-freshness/AGENT-INSTALL.md",
      "manifest_path": "templates/content-freshness/loop.yaml",
      "manifest_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/content-freshness/loop.yaml",
      "name": "Content Freshness Loop",
      "permissions": {
        "allowed_actions": [
          "read_repo",
          "read_web",
          "write_report",
          "write_state",
          "create_proposal_branch",
          "create_task"
        ],
        "credential_scopes": [
          "repo:contents:write",
          "pull_request:write",
          "kanban:create"
        ],
        "forbidden_actions": [
          "publish_publicly_without_approval",
          "rewrite_content_without_review",
          "spend_money",
          "delete_user_data",
          "mutate_source_systems"
        ],
        "summary": "6 allowed action(s), 5 forbidden action(s), 3 credential scope(s)"
      },
      "purpose": "Audit repository content for stale pages, dead links, superseded claims, and missing ownership evidence, then propose source-backed updates without publishing rewrites automatically.",
      "spec_version": "0.1",
      "trigger": {
        "default": "monthly",
        "schedule": "0 10 1 * *",
        "type": "schedule"
      },
      "triggers": [
        "schedule",
        "monthly",
        "0 10 1 * *"
      ],
      "verification": {
        "age_days": 0,
        "date": "2026-07-07",
        "details": "positive dated evidence found",
        "evidence_path": "templates/content-freshness/verification/dry-read-ambiguity-checklist.md",
        "evidence_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/content-freshness/verification/dry-read-ambiguity-checklist.md",
        "rule": "positive verification evidence auto-stales after 30 days",
        "stale_after": "2026-08-06",
        "status": "verified"
      }
    },
    {
      "backends": [
        "agent_kanban",
        "cron",
        "github_actions"
      ],
      "doc_path": "templates/dependency-release-monitor/README.md",
      "doc_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/dependency-release-monitor/README.md",
      "id": "dependency-release-monitor",
      "install_path": "templates/dependency-release-monitor/AGENT-INSTALL.md",
      "install_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/dependency-release-monitor/AGENT-INSTALL.md",
      "manifest_path": "templates/dependency-release-monitor/loop.yaml",
      "manifest_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/dependency-release-monitor/loop.yaml",
      "name": "Dependency Release Monitor Loop",
      "permissions": {
        "allowed_actions": [
          "read_web",
          "read_repo",
          "read_file",
          "write_report",
          "write_state",
          "create_proposal_branch",
          "create_task"
        ],
        "credential_scopes": [
          "repo:contents:write",
          "pull_request:write",
          "kanban:create"
        ],
        "forbidden_actions": [
          "merge_dependency_changes_without_approval",
          "change_credentials_without_approval",
          "publish_publicly_without_approval",
          "spend_money",
          "delete_user_data",
          "mutate_upstream_projects"
        ],
        "summary": "7 allowed action(s), 6 forbidden action(s), 3 credential scope(s)"
      },
      "purpose": "Watch upstream releases and changelogs for declared dependencies, assess project impact, and recommend act or ignore with confidence and risk.",
      "spec_version": "0.1",
      "trigger": {
        "default": "weekly",
        "schedule": "0 10 * * 1",
        "type": "schedule"
      },
      "triggers": [
        "schedule",
        "weekly",
        "0 10 * * 1"
      ],
      "verification": {
        "age_days": 0,
        "date": "2026-07-07",
        "details": "positive dated evidence found",
        "evidence_path": "templates/dependency-release-monitor/verification/dry-read-ambiguity-checklist.md",
        "evidence_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/dependency-release-monitor/verification/dry-read-ambiguity-checklist.md",
        "rule": "positive verification evidence auto-stales after 30 days",
        "stale_after": "2026-08-06",
        "status": "verified"
      }
    },
    {
      "backends": [
        "agent_kanban",
        "github_actions"
      ],
      "doc_path": "loops/README.md",
      "doc_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/loops/README.md",
      "id": "landscape-watch",
      "install_path": "loops/AGENT-INSTALL.md",
      "install_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/loops/AGENT-INSTALL.md",
      "manifest_path": "loops/landscape-watch.loop.yaml",
      "manifest_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/loops/landscape-watch.loop.yaml",
      "name": "Landscape Watch Loop",
      "permissions": {
        "allowed_actions": [
          "read_web",
          "read_repo",
          "write_report",
          "write_state",
          "create_proposal_branch",
          "create_task"
        ],
        "credential_scopes": [
          "repo:contents:write",
          "pull_request:write",
          "kanban:create"
        ],
        "forbidden_actions": [
          "publish_publicly_without_approval",
          "spend_money",
          "delete_user_data",
          "mutate_source_systems",
          "change_public_positioning_without_approval"
        ],
        "summary": "6 allowed action(s), 5 forbidden action(s), 3 credential scope(s)"
      },
      "purpose": "Loopmaster's own instance of the research-watch template. Polls the AI loop / agent-tooling landscape (frameworks, protocols, labs) weekly and turns new, high-signal changes into cited findings reports in docs/research/. Findings publish autonomously; public positioning or recommendation changes require human approval.\n",
      "spec_version": "0.1",
      "trigger": {
        "default": "weekly",
        "schedule": "30 9 * * 1",
        "type": "schedule"
      },
      "triggers": [
        "schedule",
        "weekly",
        "30 9 * * 1"
      ],
      "verification": {
        "details": "no positive verification evidence found under verification/",
        "rule": "positive verification evidence with a YYYY-MM-DD date is required and auto-stales after 30 days",
        "status": "unverified"
      }
    },
    {
      "backends": [
        "github_actions"
      ],
      "doc_path": "loops/README.md",
      "doc_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/loops/README.md",
      "id": "link-audit",
      "install_path": "loops/AGENT-INSTALL.md",
      "install_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/loops/AGENT-INSTALL.md",
      "manifest_path": "loops/link-audit.loop.yaml",
      "manifest_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/loops/link-audit.loop.yaml",
      "name": "Link & Source Audit Loop",
      "permissions": {
        "allowed_actions": [
          "read_repo",
          "read_web",
          "write_report",
          "update_same_host_redirects",
          "stamp_resource_status"
        ],
        "credential_scopes": [
          "contents:write_for_scheduled_report_commits"
        ],
        "forbidden_actions": [
          "replace_sources_without_approval",
          "publish_publicly_without_approval",
          "spend_money",
          "change_credentials"
        ],
        "summary": "5 allowed action(s), 4 forbidden action(s), 1 credential scope(s)"
      },
      "purpose": "Check Loopmaster documentation and resource URLs, update safe maintenance stamps, and escalate source replacement.",
      "spec_version": "0.1",
      "trigger": {
        "default": "weekly",
        "schedule": "23 10 * * 1",
        "type": "schedule"
      },
      "triggers": [
        "schedule",
        "weekly",
        "23 10 * * 1"
      ],
      "verification": {
        "age_days": 0,
        "date": "2026-07-07",
        "details": "positive dated evidence found",
        "evidence_path": "loops/log/2026-07-07-link-audit.md",
        "evidence_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/loops/log/2026-07-07-link-audit.md",
        "rule": "positive verification evidence auto-stales after 30 days",
        "stale_after": "2026-08-06",
        "status": "verified"
      }
    },
    {
      "backends": [
        "agent_kanban",
        "github_actions"
      ],
      "doc_path": "loops/README.md",
      "doc_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/loops/README.md",
      "id": "loopmaster-content-freshness",
      "install_path": "loops/AGENT-INSTALL.md",
      "install_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/loops/AGENT-INSTALL.md",
      "manifest_path": "loops/loopmaster-content-freshness.loop.yaml",
      "manifest_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/loops/loopmaster-content-freshness.loop.yaml",
      "name": "Loopmaster Content Freshness Loop",
      "permissions": {
        "allowed_actions": [
          "read_repo",
          "read_web",
          "write_report",
          "write_state",
          "create_proposal_branch",
          "create_task"
        ],
        "credential_scopes": [
          "repo:contents:write",
          "pull_request:write",
          "kanban:create"
        ],
        "forbidden_actions": [
          "publish_publicly_without_approval",
          "rewrite_content_without_review",
          "change_public_positioning_without_approval",
          "spend_money",
          "delete_user_data",
          "mutate_source_systems"
        ],
        "summary": "6 allowed action(s), 6 forbidden action(s), 3 credential scope(s)"
      },
      "purpose": "Audit Loopmaster's public docs, learning content, resource metadata, and loop guides for stale claims, broken links, and unresolved freshness markers; report proposals without rewriting public positioning autonomously.",
      "spec_version": "0.1",
      "trigger": {
        "default": "monthly",
        "schedule": "0 10 1 * *",
        "type": "schedule"
      },
      "triggers": [
        "schedule",
        "monthly",
        "0 10 1 * *"
      ],
      "verification": {
        "details": "no positive verification evidence found under verification/",
        "rule": "positive verification evidence with a YYYY-MM-DD date is required and auto-stales after 30 days",
        "status": "unverified"
      }
    },
    {
      "backends": [
        "agent_kanban",
        "cron",
        "github_actions"
      ],
      "doc_path": "templates/research-watch/README.md",
      "doc_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/research-watch/README.md",
      "id": "research-watch",
      "install_path": "templates/research-watch/AGENT-INSTALL.md",
      "install_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/research-watch/AGENT-INSTALL.md",
      "manifest_path": "templates/research-watch/loop.yaml",
      "manifest_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/research-watch/loop.yaml",
      "name": "Research Watch Loop",
      "permissions": {
        "allowed_actions": [
          "read_web",
          "read_repo",
          "write_report",
          "write_state",
          "create_proposal_branch",
          "create_task"
        ],
        "credential_scopes": [
          "repo:contents:write",
          "pull_request:write",
          "kanban:create"
        ],
        "forbidden_actions": [
          "publish_publicly_without_approval",
          "spend_money",
          "delete_user_data",
          "mutate_source_systems"
        ],
        "summary": "6 allowed action(s), 4 forbidden action(s), 3 credential scope(s)"
      },
      "purpose": "Monitor trusted sources and turn new, high-signal research changes into cited findings reports and optional follow-up tasks.",
      "spec_version": "0.1",
      "trigger": {
        "default": "weekly",
        "schedule": "0 9 * * 1",
        "type": "schedule"
      },
      "triggers": [
        "schedule",
        "weekly",
        "0 9 * * 1"
      ],
      "verification": {
        "age_days": 0,
        "date": "2026-07-07",
        "details": "positive dated evidence found",
        "evidence_path": "templates/research-watch/verification/dry-read-ambiguity-checklist.md",
        "evidence_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/templates/research-watch/verification/dry-read-ambiguity-checklist.md",
        "rule": "positive verification evidence auto-stales after 30 days",
        "stale_after": "2026-08-06",
        "status": "verified"
      }
    },
    {
      "backends": [
        "agent_kanban",
        "cron",
        "github_actions"
      ],
      "doc_path": "loops/README.md",
      "doc_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/loops/README.md",
      "id": "resource-discovery",
      "install_path": "loops/AGENT-INSTALL.md",
      "install_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/loops/AGENT-INSTALL.md",
      "manifest_path": "loops/resource-discovery.loop.yaml",
      "manifest_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/loops/resource-discovery.loop.yaml",
      "name": "Resource Discovery Loop",
      "permissions": {
        "allowed_actions": [
          "read_web",
          "read_repo",
          "write_report",
          "write_state",
          "create_proposal_branch",
          "create_task"
        ],
        "credential_scopes": [
          "repo:contents:write",
          "pull_request:write",
          "kanban:create"
        ],
        "forbidden_actions": [
          "publish_publicly_without_approval",
          "merge_resource_entries_without_approval",
          "spend_money",
          "delete_user_data",
          "mutate_source_systems"
        ],
        "summary": "6 allowed action(s), 5 forbidden action(s), 3 credential scope(s)"
      },
      "purpose": "Sweep committed sources and rotating queries each week, score candidates against the resource rubric, and propose ready-to-merge entries for the curated library without publishing them.",
      "spec_version": "0.1",
      "trigger": {
        "default": "weekly",
        "schedule": "30 9 * * 1",
        "type": "schedule"
      },
      "triggers": [
        "schedule",
        "weekly",
        "30 9 * * 1"
      ],
      "verification": {
        "details": "no positive verification evidence found under verification/",
        "rule": "positive verification evidence with a YYYY-MM-DD date is required and auto-stales after 30 days",
        "status": "unverified"
      }
    }
  ]
}

## END registry/index.json

## BEGIN skills/index.json

{
  "schema_version": "lm-skills-01",
  "skills": [
    {
      "backends": [
        "cron",
        "github_actions",
        "agent_kanban"
      ],
      "category": "authoring",
      "deploys_template": null,
      "id": "loopify",
      "name": "Loopify",
      "requirements": [
        "repository checkout containing spec/loop.schema.json",
        "free-text workflow description or notes from the human operator",
        "optional artifacts such as scripts, checklists, sample inputs, or previous cron entries",
        "uv with pyyaml and jsonschema, or check-jsonschema with pyyaml, for manifest validation",
        "shell access for deterministic verify.sh dry-runs"
      ],
      "skill_url": "https://loopmaster-ai.pages.dev/skills/loopify/SKILL.md",
      "summary": "Use when a human describes a manual workflow and needs Q&A intake plus a draft Loopmaster loop bundle: loop.yaml, README, AGENT-INSTALL.md, verify.sh, and registry-entry instructions.",
      "verification": {
        "details": "no verification evidence found under verification/",
        "status": "unverified"
      }
    },
    {
      "backends": [
        "cron",
        "github_actions",
        "agent_kanban"
      ],
      "category": "authoring",
      "deploys_template": "research-watch",
      "id": "deploy-your-first-loop",
      "name": "Deploy Your First Loop",
      "requirements": [
        "Python 3",
        "repository checkout containing templates/research-watch",
        "uv for manifest validation",
        "cron for the local scheduler backend, or GitHub Actions / Hermes kanban for alternate backends",
        "no web-search API key for the default research-watch run"
      ],
      "skill_url": "https://loopmaster-ai.pages.dev/skills/deploy-your-first-loop/SKILL.md",
      "summary": "Use when an agent or human wants to deploy the research-watch Loopmaster template through cron, GitHub Actions, or agent-kanban and verify a running loop in one session.",
      "verification": {
        "date": "2026-07-07",
        "details": "positive dated skill verification evidence found",
        "evidence_path": "skills/getting-started/deploy-your-first-loop/verification/cron-scratch-transcript.md",
        "evidence_url": "https://github.com/chrismaddern/loopmaster.ai/blob/main/skills/getting-started/deploy-your-first-loop/verification/cron-scratch-transcript.md",
        "status": "verified"
      }
    }
  ]
}

## END skills/index.json

## BEGIN skill index

- id: deploy-your-first-loop
  name: Deploy Your First Loop
  description: Use when an agent or human wants to deploy the research-watch Loopmaster template through cron, GitHub Actions, or agent-kanban and verify a running loop in one session.
  deploys_template: research-watch
  backends: cron, github_actions, agent_kanban
  skill_url: https://loopmaster-ai.pages.dev/skills/deploy-your-first-loop/SKILL.md
- id: loopify
  name: Loopify
  description: Use when a human describes a manual workflow and needs Q&A intake plus a draft Loopmaster loop bundle: loop.yaml, README, AGENT-INSTALL.md, verify.sh, and registry-entry instructions.
  backends: cron, github_actions, agent_kanban
  skill_url: https://loopmaster-ai.pages.dev/skills/loopify/SKILL.md

## END skill index

## BEGIN docs/AGENT-GUIDE.md

# Agent guide

This guide is for agents that are given only the Loopmaster repository URL and need to choose, install, and verify a loop template without human hand-holding.

Repository URL:

- `https://github.com/chrismaddern/loopmaster.ai`

Raw fetch base for direct file reads:

- `https://raw.githubusercontent.com/chrismaddern/loopmaster.ai/main/`

## Six-step flow

### 1. Discover

Fetch the agent entry point, then the generated catalog.

Exact paths:

- `llms.txt`
- `registry/index.json`

Raw URLs:

- `https://raw.githubusercontent.com/chrismaddern/loopmaster.ai/main/llms.txt`
- `https://raw.githubusercontent.com/chrismaddern/loopmaster.ai/main/registry/index.json`

Use `llms.txt` for the repo usage contract and `registry/index.json` for structured fields: `id`, `name`, `purpose`, `triggers`, `permissions`, `verification`, `manifest_path`, `install_path`, and `doc_path`.

### 2. Select

Match the user's goal against the catalog entry fields.

Use these fields first:

- `purpose` — what the loop is for.
- `triggers` — when it should run.
- `backends` — supported runtimes such as `cron`, `github_actions`, or `agent_kanban`.
- `permissions.summary`, `permissions.allowed_actions`, `permissions.forbidden_actions`, and `permissions.credential_scopes` — whether the loop is safe and possible in the current environment.
- `verification.status`, `verification.date`, and `verification.evidence_path` — whether the loop has current positive evidence.

Do not silently substitute a different template. If no template matches the goal, report the gap or create an appropriately scoped follow-up task.

### 3. Read

For the selected template, fetch both the machine contract and the install guide from the paths in the catalog.

Example: research-watch.

- Manifest path: `templates/research-watch/loop.yaml`
- Install path: `templates/research-watch/AGENT-INSTALL.md`
- Human guide path: `templates/research-watch/README.md`

Raw URLs:

- `https://raw.githubusercontent.com/chrismaddern/loopmaster.ai/main/templates/research-watch/loop.yaml`
- `https://raw.githubusercontent.com/chrismaddern/loopmaster.ai/main/templates/research-watch/AGENT-INSTALL.md`
- `https://raw.githubusercontent.com/chrismaddern/loopmaster.ai/main/templates/research-watch/README.md`

Treat `loop.yaml` as the authority for what the loop may do. Treat `AGENT-INSTALL.md` as the authority for exact setup commands, expected outputs, and backend-specific wiring.

### 4. Install

Create only the files, state paths, schedules, tasks, or workflow entries declared by the selected template and install guide.

Before writing or scheduling anything, check:

- `inputs` for required source files, environment variables, and runtime files.
- `state.paths` for persistent state locations.
- `outputs` for expected reports, notifications, and task creation.
- `backends` for the chosen runtime's install notes.
- `human_gates.required_for` for actions that require approval.

If a credential is missing, do not invent it or broaden scope. Stop at the relevant human gate and report the exact missing scope.

### 5. Verify

Run the selected template's `verification.commands` and check every `verification.required` assertion before reporting success.

Example: research-watch manifest validation command from `templates/research-watch/loop.yaml`:

```sh
uv run --with check-jsonschema --with pyyaml check-jsonschema --schemafile spec/loop.schema.json templates/research-watch/loop.yaml
```

Example: research-watch local dry run from the same manifest:

```sh
python3 templates/research-watch/scripts/research_watch.py --sources templates/research-watch/examples/dry-run-sources.json --state /tmp/loopmaster-research-watch-state.json --output-dir /tmp/loopmaster-research-watch --max-items 5
```

A successful install report should name the commands run, exit codes, key output paths, and any assertions that could not be checked.

### 6. Escalate

Escalate instead of guessing when any of these happen:

- A `human_gates.required_for` action is needed.
- A required credential or permission scope is missing.
- A verification command fails.
- The template asks to spend money, publish publicly, delete data, mutate source systems, or change public positioning.
- The install guide and manifest disagree.
- The registry marks the chosen entry `unverified` or its evidence is stale, and the user asked for a proven loop.

When escalating, include the selected template id, the exact path or field that caused the stop, what was already fetched, and the next safe action.

## Three-fetch manifest reachability test

An agent with only the repository URL can reach a chosen template manifest in three fetches:

1. `GET https://raw.githubusercontent.com/chrismaddern/loopmaster.ai/main/llms.txt`
2. `GET https://raw.githubusercontent.com/chrismaddern/loopmaster.ai/main/registry/index.json`
3. Read `templates[].manifest_path` for the chosen id, then `GET https://raw.githubusercontent.com/chrismaddern/loopmaster.ai/main/<manifest_path>`.

For `research-watch`, fetch 3 is:

- `https://raw.githubusercontent.com/chrismaddern/loopmaster.ai/main/templates/research-watch/loop.yaml`

The same pattern works for every catalog entry that includes `manifest_path`.

## END docs/AGENT-GUIDE.md