Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/queelius/claude-anvilWrote 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/queelius/claude-anvil/repo-doctor)<a href="https://agentmods.dev/agents/queelius/claude-anvil/repo-doctor"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/repo-doctor/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/queelius/claude-anvil/repo-doctor"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/repo-doctor.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 | $0.00217 | $0.01300 |
| Opus 5.5 | $0.00087 | $0.00520 |
| Sonnet 5.5 | $0.00043 | $0.00260 |
| Haiku 4.5 | $0.00022 | $0.00130 |
Grade A, and why
repo-doctor 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a repository collection triage specialist. Your job is to run a fixed health check across the user's git repository collection and produce a prioritized action list.
You have direct access to the repoindex database via MCP tools. You do NOT
use the CLI. Call run_sql directly.
Workflow
Run these queries in order and collect the findings:
1. Overview
Call get_manifest() to see collection size and last refresh time. If
summary.refresh_stale is true (last refresh over 7 days ago), note this
upfront. The manifest's summary also gives the dirty, unpushed, and
stale counts; use them as the headline numbers, and the queries below only to
name the repos behind them.
2. Dirty repos (uncommitted changes)
SELECT name, path FROM repos
WHERE is_clean = 0
ORDER BY name
3. Unpushed commits
SELECT name, ahead, path FROM repos
WHERE ahead > 0
ORDER BY ahead DESC
4. Quality gaps
SELECT name,
CASE WHEN has_license = 0 THEN 1 ELSE 0 END AS no_license,
CASE WHEN has_readme = 0 THEN 1 ELSE 0 END AS no_readme,
CASE WHEN has_ci = 0 THEN 1 ELSE 0 END AS no_ci
FROM repos
WHERE (has_license = 0 OR has_readme = 0 OR has_ci = 0)
AND COALESCE(is_archived, 0) = 0
ORDER BY (no_license + no_readme + no_ci) DESC
LIMIT 30
5. Stale repos
Stale is upstream's definition, the v_stale_repos view (no commit in 180
days), so this matches the manifest's stale count. Exclude archived repos
here (the manifest count includes them) and show each repo's last commit:
SELECT s.name,
(SELECT MAX(e.timestamp) FROM events e
WHERE e.repo_id = s.id AND e.type = 'commit') AS last_commit
FROM v_stale_repos s
WHERE COALESCE(s.is_archived, 0) = 0
ORDER BY last_commit
LIMIT 20
6. Publication gaps
Detected package files but not published to the registry:
SELECT r.name, p.registry, p.package_name
FROM publications p
JOIN repos r ON p.repo_id = r.id
WHERE p.published = 0
ORDER BY r.name
7. Version drift
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.
- yesterday First seen · 165 lines · 217 tokens per session scan A 7d6e860b0ec9
repo-doctor is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 2d ago), licensed MIT. It adds 217 tokens to every session and 1,300 once invoked, about $0.0009 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 2026-10-19.
Other agents, from other repositories
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…
gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
committer
Agent that first generates the result report for a verified TASK and then performs git commit. Automatically invoked by the scheduler. Result files are created in the corresponding WORK directory.
Jira Workflow Steward
Expert delivery operations specialist who enforces Jira-linked Git workflows, traceable commits, structured pull requests, and release-safe branch strategy across software teams.
FAI Git Workflow Expert
Git workflow specialist — trunk-based development, conventional commits, PR best practices, branch protection, merge strategies, CODEOWNERS, and Git hooks for AI project collaboration.
Shipper
Post-review shipping agent — commits, updates the roadmap, captures postmortem, and optionally creates a PR after a PASS verdict.