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-mirror)<a href="https://agentmods.dev/commands/queelius/claude-anvil/repo-mirror"><img src="https://agentmods.dev/badge/commands/queelius/claude-anvil/repo-mirror/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-mirror"><img src="https://agentmods.dev/badge/commands/queelius/claude-anvil/repo-mirror.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 | $0.00025 | $0.00929 |
| Opus 5.5 | $0.00010 | $0.00372 |
| Sonnet 5.5 | $0.00005 | $0.00186 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
repo-mirror 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/repo-mirror
Thin wrapper around repoindex ops mirror. Pushes every branch and tag (git push --mirror) to one or more redundancy targets configured in ~/.repoindex/config.yaml.
Safety: Runs with --dry-run by default. The real push only happens if the user explicitly passes --force-real (this slash command translates that to dropping --dry-run when invoking the CLI).
Arguments (forwarded)
Pick at least one target selector:
| Flag | Effect |
|---|---|
--to codeberg |
Push to one named mirror (repeatable) |
--all |
Push to every configured mirror |
Repo filters (optional):
| Flag | Effect |
|---|---|
--language python |
Only Python repos |
--tag work/active |
Only repos with this tag |
--recent 7d |
Only repos with recent commits |
--dirty |
Only repos with uncommitted changes (rare for mirroring) |
Special flags:
| Flag | Effect |
|---|---|
--init |
For file:// targets, init a bare repo at the destination if missing |
--force |
Bypass fast-forward check (overwrites diverged branches on the mirror) |
--force-real |
THIS COMMAND ONLY: drop the automatic --dry-run and actually push |
Workflow
Step 1: Check that mirrors are configured
Run:
repoindex config get forges 2>&1
It prints the forges mapping as JSON, or Key not found: forges (on stderr) when none is configured. If it is not found, or no entry has role: mirror, stop and print a config template:
forges:
codeberg:
source_id: gitea
host: codeberg.org
role: mirror
token_env: CODEBERG_TOKEN
url_template: "https://codeberg.org/queelius/{repo}.git"
gitea-gdrive:
source_id: gitea
role: mirror
url_template: "file:///mnt/gdrive/git-mirrors/{repo}.git"
Explain that {repo} is substituted with the repo name, that SSH URLs ([email protected]:queelius/{repo}.git) work too, and that role: mirror is what makes ops mirror recognize the entry. Do not proceed to step 2.
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 · 111 lines · 25 tokens per session scan A aba807f39e6d
repo-mirror is a command published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 929 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-review
Perform exhaustive code reviews using multi-agent analysis, ultra-thinking, and worktrees.
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.
prune-sync-log
Prune stale entries from the whetstone sync decision log.
ia-changelog
Create engaging changelogs for recent merges to main branch.
release
Bump version, commit, push, mirror to ai-skills, and update local plugin.
sm-sail
Command "sm-sail" from ScienceIsNeato/slop-mop, covering /sm-sail — drive a pr to green, autonomously, the loop, when sail parks on review threads, when to stop before "pr ready" — only two reasons and expect convergence, not one pass.