tested 2026-07-07 ✓
Agent Usability Test Loop
Run a clean-room agent through template or site docs and turn transcript details into a pass/fail friction report.
Templates
Loop templates
Your agent is about to install something and run it unattended. Before it does, it needs three facts: what has been tried, what passed, and what still needs a human. Tested means the template's checks ran and passed on a date you can see. Not tested yet means exactly that — look, but don't trust it unattended.
Every template is described twice: a guide for you, and a manifest for your agent. The manifest, a small file called loop.yaml, is the loop's job description: what may start it, what it's allowed to do, what it must never do, how its work gets checked, and when it must stop and ask a human.
tested 2026-07-07 ✓
CI Repair Loop
Detect a failing CI signal, inspect the failure details, make the smallest justified patch, rerun verification, and open or update a pull request without masking the real issue.
tested 2026-07-07 ✓
Content Freshness Loop
Check repository content for stale pages, dead links, superseded claims, and missing ownership records, then propose source-backed updates without publishing rewrites automatically.
tested 2026-07-07 ✓
Dependency Release Monitor Loop
Watch upstream releases and changelogs for declared dependencies, assess project impact, and recommend act or ignore with confidence and risk.
not tested yet
Landscape Watch Loop
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.
tested 2026-07-07 ✓
Link & Source Check Loop
Check Loopmaster documentation and resource URLs, update safe maintenance stamps, and escalate source updates.
not tested yet
Loopmaster Content Freshness Loop
Check 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.
tested 2026-07-07 ✓
Research Watch Loop
Monitor trusted sources and turn new, high-signal research changes into cited findings reports and optional follow-up tasks.
not tested yet
Resource Discovery Loop
Sweep committed sources and rotating queries each week, score candidates against the resource selection notes, and propose ready-to-merge entries for the curated library without publishing them.