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/commands/queelius/claude-anvil/repo-status)<a href="https://agentmods.dev/commands/queelius/claude-anvil/repo-status"><img src="https://agentmods.dev/badge/commands/queelius/claude-anvil/repo-status/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/commands/queelius/claude-anvil/repo-status"><img src="https://agentmods.dev/badge/commands/queelius/claude-anvil/repo-status.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 | $0.00022 | $0.00779 |
| Opus 5.5 | $0.00009 | $0.00312 |
| Sonnet 5.5 | $0.00004 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
repo-status 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/repo-status
Quick, read-only status view. Two modes depending on whether a repo name is passed.
Mode 1: No argument (collection overview)
- Call
mcp__repoindex__get_manifest(). - Format the response concisely, not as raw JSON. Include:
- Total repos, total events, last refresh timestamp.
- Language breakdown (top 5 by repo count).
- Health counts from
summary:dirty,unpushed,stale(no commit in 180 days),published/unpublished,doi_count. - A staleness warning when
summary.refresh_staleis true (last refresh over 7 days ago): flag it and suggestmcp__repoindex__refresh().
- Keep the output under 15 lines. This is a glanceable dashboard.
Mode 2: With a repo name argument
The argument is a repo name (possibly a fragment). Resolve it with fuzzy matching.
Step 1: Resolve the name
SELECT id, name, path, language, description, is_clean, ahead, behind
FROM repos
WHERE name = ? OR name LIKE ?
ORDER BY CASE WHEN name = ? THEN 0 ELSE 1 END, name
LIMIT 5
If multiple matches, show the list and ask which one.
If zero matches, try a broader fuzzy search:
SELECT name, path FROM repos
WHERE name LIKE '%NAME%'
ORDER BY name
LIMIT 10
Step 2: Detail view
Once a single repo is identified, run these three queries in parallel:
-- Main row
SELECT name, path, language, description, is_clean, ahead, behind,
has_readme, has_license, has_ci, has_citation, has_codemeta,
stars, forks_count, topics, forge_description,
is_archived
FROM repos WHERE id = ?
-- Recent events (last 30 days, max 15 rows)
SELECT type, timestamp, ref, message
FROM events
WHERE repo_id = ? AND timestamp > datetime('now', '-30 days')
ORDER BY timestamp DESC
LIMIT 15
-- Publications
SELECT registry, package_name, current_version, published, downloads_30d, doi
FROM publications WHERE repo_id = ?
Step 3: Render
Show a compact repo card:
repo-name (language, github stars, path)
description line if present
Git: clean / dirty, N ahead, M behind
Quality: readme ok, license ok, ci missing, citation missing
Publications: pypi 0.15.0 published, 3421 downloads 30d
Recent activity (last 30 days):
git_tag 2d ago v0.16.0
commit 3d ago feat: ...
...
Flags: archived, fork, private (only if any are true)
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 · 104 lines · 22 tokens per session scan A a7888ccab1df
repo-status is a command published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 779 once invoked, about $0.0001 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 commands, from other repositories
stacked-prs
Create semantic commits split into stacked upstream PRs under 600 lines each.
pre-commit-check
Tu es un assistant de qualité code. Tu dois effectuer toutes les vérifications nécessaires AVANT de créer un commit, pour garantir que le code respecte les standards du projet.
replay
You are reconstructing the historical evolution of this sprint by recompiling every version of claims.json from git history.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
fest-commit
Commit changes with festival traceability metadata.
genshijin-commit
A command that writes a commit message for changes already placed in Git's staging area. It follows the repository's existing language and uses a short imperative subject without AI attribution.