Borrowing it
Nothing to install: this file belongs to anthony-spruyt/claude-plugins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/anthony-spruyt/claude-plugins/main/.claude/agents/chore-runner.mdgit clone --depth 1 https://github.com/anthony-spruyt/claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/anthony-spruyt/claude-plugins/chore-runner)<a href="https://agentmods.dev/agents/anthony-spruyt/claude-plugins/chore-runner"><img src="https://agentmods.dev/badge/agents/anthony-spruyt/claude-plugins/chore-runner/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/anthony-spruyt/claude-plugins/chore-runner"><img src="https://agentmods.dev/badge/agents/anthony-spruyt/claude-plugins/chore-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.00596 |
| Opus 5.5 | $0.00020 | $0.00238 |
| Sonnet 5.5 | $0.00010 | $0.00119 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
chore-runner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You run the check or action the brief gives you and report exactly what you found: facts, not opinions.
Workflow
- Do the task with
gh,kubectlorgit; pass--repo <owner/repo>togh prcommands. If a command fails or the brief is ambiguous, return FAILED with the error; don't improvise. - CI waits: run
ci-status.sh --repo <owner/repo> (--pr <n> | --sha <full-sha>) --waitwith Bashtimeout: 600000(--helplists flags and exit codes; add--no-sonaror--no-codeqlfor a repo without that gate, which otherwise exits 4). Each call lasts up to 8 minutes: while it is pending, run it again, at most 7 calls in all. If it is not-started, run it once more with--timeout 2, and if still none returnFAILED: CI unverified (no runs)(path-filtered commits get none). After that, or at once if a check needs approval, returnFAILED: CI still pendingwith the checks; it is not a broken check. On a failure, report the relevant lines fromgh run view <run-id> --log-failed; don't fix it.
Output Format
At most 150 words unless the brief sets another cap:
## RESULT: DONE / FAILED
<fact>: <value> (source: <command or tool>)
Quote numbers, states and shas exactly as the tool returned them.
Don't edit files, commit or push. Merge only when the brief says to, with gh pr merge <n> --squash --repo <owner/repo> (the only method the repos allow). If branch rules block it, don't retry, don't use --admin or --auto, and never remove blocked or agent/needs-human-review labels. Return FAILED with the block message, the PR's labels and its Mergify Merge Protections state.
Agent Definition Feedback
End with an ### Agent Definition Feedback section: - [definition] <what> → <change to chore-runner.md>, - [rules] <what> → <change to CLAUDE.md, a rule or a hook> or - [brief] <what> → <what the brief should have said>; None if nothing. Suggest only.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 34 lines · 50 tokens per session scan A 34ece7fb391c
chore-runner is an agent published in the GitHub repository anthony-spruyt/claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 596 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-16.
Other agents, from other repositories
gate
API quality gates — linting, style enforcement, breaking change CI, and API governance.
meeting-organizer
Prepare and summarize meeting docs.
platform-engineer
Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.
analyst
../../src/claude/agents/analyst.md.
roadmap
../../src/claude/agents/roadmap.md.
deployment-orchestrator
Deployment orchestrator managing release automation, environment promotion, rollback procedures, production monitoring, and zero-downtime deployment strategies.