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-week)<a href="https://agentmods.dev/commands/queelius/claude-anvil/repo-week"><img src="https://agentmods.dev/badge/commands/queelius/claude-anvil/repo-week/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-week"><img src="https://agentmods.dev/badge/commands/queelius/claude-anvil/repo-week.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 | $0.00019 | $0.00777 |
| Opus 5.5 | $0.00008 | $0.00311 |
| Sonnet 5.5 | $0.00004 | $0.00155 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
repo-week 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/repo-week
Summarize recent activity across the repository collection. Default window is 7 days.
Arguments
- No argument: use 7 days.
- One argument like
7d,14d,30d,90d: parse the integer and use that many days. - If the argument does not match
\d+d, fall back to 7 days and note this at the top.
Workflow
Call mcp__repoindex__run_sql with the queries below, substituting the chosen window into datetime('now', '-N days').
1. Top repos by commit churn
SELECT r.name, r.language, COUNT(*) AS commits, MAX(e.timestamp) AS last
FROM events e JOIN repos r ON e.repo_id = r.id
WHERE e.type = 'commit' AND e.timestamp > datetime('now', '-7 days')
GROUP BY r.id
ORDER BY commits DESC
LIMIT 15
2. Releases in the window
Git tags, plus forge release events when forge events have been refreshed (refresh(forge_events=true); off by default). The same release often appears as both, so dedupe by ref.
SELECT r.name, e.type, e.ref, e.timestamp, e.message
FROM events e JOIN repos r ON e.repo_id = r.id
WHERE e.type IN ('git_tag', 'release') AND e.timestamp > datetime('now', '-7 days')
ORDER BY e.timestamp DESC
3. Overall totals
SELECT type, COUNT(*) AS n
FROM events
WHERE timestamp > datetime('now', '-7 days')
GROUP BY type
ORDER BY n DESC
4. Dormant repos that woke up
Repos with activity in the window but no prior activity in the 30 days before that:
WITH recent AS (
SELECT DISTINCT repo_id FROM events
WHERE type = 'commit' AND timestamp > datetime('now', '-7 days')
),
before AS (
SELECT DISTINCT repo_id FROM events
WHERE type = 'commit'
AND timestamp BETWEEN datetime('now', '-37 days') AND datetime('now', '-7 days')
)
SELECT r.name, r.language FROM repos r
JOIN recent rc ON rc.repo_id = r.id
LEFT JOIN before b ON b.repo_id = r.id
WHERE b.repo_id IS NULL
ORDER BY r.name
Output
Keep it scannable. Suggested layout:
Week in review (last N days)
Commits: X across Y repos
Releases: Z tags across W repos
Top churn
repo-a (python) 42 commits, last 2h ago
repo-b (rust) 18 commits, last 1d ago
...
Releases
repo-a v0.16.0 2 days ago
...
Woke up
repo-c, repo-d
Quiet week across the rest.
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 · 109 lines · 19 tokens per session scan A de702145ddfa
repo-week is a command published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 777 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
ia-document-release
Post-ship documentation sync. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, and optionally bumps the version.
ia-changelog
Create engaging changelogs for recent merges to main branch.
commit
Smart conventional commit with security validation, branch flow enforcement, and auto-detection. Use for git commit, commit changes, save work, stage and commit.
release
Bump version, commit, push, mirror to ai-skills, and update local plugin.
flow
Universal workflow entry point. Use /flow for skill-driven GitHub development. Verbs: start, commit, pr, review, address, merge, resolve, release, status, learn, setup, explain, debug, design, brainstorm, issue.
release
Generate changelog, bump version, and create git tag.