Autonomous coding loop for long-running tasks (refactors, new features, test sweeps). A Python harness owns the state machine and runs one phase at a time as its own headless process — scout, worker, gate, render, evaluate, commit, learn, with a judge on any failure path — each with its own model tier, timeout, budget and usage record. It enforces the allow-list, screenshots the product and checks copy tasks for real similarity before anything commits, resumes or splits a timed-out worker instead of losing the tick, and settles the decisions it can settle on its own into an auditable ledger rather than waking a human. Pause and Stop land at a phase boundary; a browser dashboard shows the phase in flight, the screenshots and the decisions. On an incident it runs a budgeted /agent-loop-medic that repairs only from an allowlist and hands over to a human (NEEDS_HUMAN.md, exit 2) when it cannot. Requires the superpowers plugin; bundles the postmortem plugin and recommends the permissions plugin for its /permissions-advisor pre-flight check.
Plugin agent-loop from marketplace claude-toolbelt in mitcsutt/claude-toolbelt. Commands read from the repo's manifest — 16 days ago.
agent-loop-medicBounded triage-and-repair for an agent-loop incident. Invoked headless by run.sh on an incident ("/agent-loop-medic <id>"), by /agent-loop's incident monitor, or by hand. Reads the incident, judges harness/tick liveness from the runtime files (not the process table), applies only allowlisted fixes u
agent-loop-postmortemThis skill should be used to close out an autonomous coding loop and produce a retrospective. Aggregates loop artefacts (LOOP_CONFIG.md, LOOP_PLAN.md, LOOP_USAGE.jsonl, LOOP_CLEANUP.md, Loop-Status commit trailers) into a dense structured context, then delegates to /postmortem to write the document.
agent-loop-setupUse to bootstrap an autonomous coding loop for refactors, new features, test sweeps, or other long-running multi-task work. Interactive, one-time setup that prepares loop artefacts inside a git worktree, then prints a launch command for the bash harness (run.sh) — which re-invokes a fresh headless C
agent-loopAttach an interactive session to the current repo's agent-loop. Reports harness/tick health from the runtime files, ensures exactly one detached dashboard (reused or launched with --detach; it survives this session), arms an incident monitor so this session is woken to run /agent-loop-medic when the
A library of ten read-only persona reviewer subagents (grumpy senior, paranoid SRE, fact-checker, DX advocate, threat modeller, goal auditor, outsider, contract keeper, cost hawk, noise filter) and an /assemble-panel skill that picks the right panel for a plan, spec, diff or decision, briefs and dispatches it in parallel, and filters the reports into one triage.
1 skill · 10 agents
Retrieves up-to-date technical documentation, code examples, and performs people/company research using Context7 MCP and Exa AI MCP
2 skills · 2 MCP servers
Finds unsafe, dead and contradictory permission rules across managed/user/project/local settings. SessionStart alert, /permissions-review, /permissions-advisor, perm-scan and perm-apply commands. No per-call hooks. Points to the built-in /fewer-permission-prompts for new allow rules.
2 skills · hooks
Generic git and GitHub helper skills. Currently ships gh-pending-review (add inline comments to an existing pending PR review without overwriting or duplicating it, via GraphQL); a home for future git/GitHub skills.
1 skill
Token-frugal orchestration doctrine for an expensive top-level model: reserve the expensive tier for judgment, route token-heavy bounded work to the cheapest capable subagent tier, demand compact returns with traceable source references, and vet before acting. Model- and harness-agnostic.
1 skill
Generic structured retrospective generator. Writes searchable postmortem documents to docs/postmortems/ with an 8-section template. Callable after any significant task.
1 skill
Scaffold, validate, and publish new Claude Code plugins with proper structure
3 skills · 1 command · 1 agent
Claude Code skill for creating and presenting Slidev slidedecks
1 skill
Observability plugin for Claude Code with MLflow tracing
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
3 skills
Connect to your Phoenix instance to debug, evaluate, and improve LLM applications.
1 MCP server
OpenRouter for tools - 4,000+ agent-friendly tools, pay for the usage, not subscription
1 skill · 1 MCP server
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.