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.
npx skills add queelius/claude-anvil --skill mfgit 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/skills/queelius/claude-anvil/mf)<a href="https://agentmods.dev/skills/queelius/claude-anvil/mf"><img src="https://agentmods.dev/badge/skills/queelius/claude-anvil/mf/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/skills/queelius/claude-anvil/mf"><img src="https://agentmods.dev/badge/skills/queelius/claude-anvil/mf.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 | $0.00058 | $0.02610 |
| Opus 5.5 | $0.00023 | $0.01044 |
| Sonnet 5.5 | $0.00012 | $0.00522 |
| Haiku 4.5 | $0.00006 | $0.00261 |
Grade A, and why
mf 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mf: Metafunctor Site Management
Interpret the user's intent, then run the right mf CLI workflow. mf does the mechanics (database CRUD, Hugo content generation, front matter edits); you do the judgment (choosing and sequencing commands, writing content).
Preflight
- Right binary. TeX Live ships a
/usr/bin/mf(Metafont) that shadows the metafunctor CLI when the latter is not earlier on PATH. Before the firstmfcommand in a session, runmf --versionand expectmf, version .... Anything else (aThis is METAFONTbanner, or a prompt waiting for input) means the CLI is not on PATH: stop and tell the user to install it withuv tool install -e ~/github/repos/mf(which puts it in~/.local/bin), rather than running commands against the wrong program. - Site facts. Resolve the site root:
mf config pathprints<site root>/.mf/config.yaml(it honorsMF_SITE_ROOTand the global config). Then Read<site root>/CLAUDE.mdbefore writing or editing content. It is the single source of truth for taxonomies and their front-matter keys, front matter fields, bundle types, build and deploy, and site gotchas. Do not rely on memory for these.ls <site root>/content/is the authoritative section list; read a section's_index.mdbefore adding to it.
Field lists for the databases come from the CLI itself: mf papers fields, mf projects fields, mf series fields, mf packages fields.
Content Source Model
| Content | Ground truth | mf role | Database |
|---|---|---|---|
| Projects | GitHub repos | import/sync + overrides + generate | projects_db.json |
| Papers | Built paper repos (LaTeX) | ingest + set + generate | paper_db.json |
| Series | External source repos (source_dir) |
sync (pull by default) + landing pages | series_db.json |
| Publications | Venue lifecycle (submissions, acceptances, DOIs) | add/update/log/pull + generate | pubs_db.json (independent of paper_db) |
| Packages | PyPI/CRAN registries | add/sync + generate | packages_db.json |
| Posts | The .md file |
mf posts front matter edits |
none |
| Writing, essays, other sections | The .md file |
none | none |
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.
- 12d ago Changed · -122 lines · -3 tokens per session 6c9159784cbb
- 15d ago Changed · +1 lines b7ab59f16a42
- 2mo ago First seen · 258 lines · 61 tokens per session scan A 7fad7c262c83
mf is a skill published in the GitHub repository queelius/claude-anvil (2 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 2,610 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 2026-08-31.
Other skills, from other repositories
renovate
Generate renovate.json covering all dependency file types used in a repo, emit a GitHub Actions workflow that validates renovate.json on every PR, or generate a pre-commit hook for local validation.
gitops
Flux CD and Argo CD — two modes. debug: five structured debug workflows for live clusters (installation, source, HelmRelease, Kustomization, ResourceSet) producing a five-section report. audit: six-phase read-only repo analysis (discovery, validation, API compliance, best practices, security) producing a prioritised…
commit
Analyze git diffs or staged changes and generate conventional commit messages that explain WHY a change was made. Supports auto-detecting type and scope, intelligent file staging, and interactive overrides. Use when asked to "write a commit message", "generate a commit", "describe my changes", "commit this"…
secrets-scan
Scans git-tracked files for leaked secrets. Triggers - secrets scan, find credentials, leaked keys, security audit.
docsync-setup
Installs project-local doc-staleness tracking (hooks) and reports/forces doc sync. Triggers: docsync, track doc staleness, doc sync status, stale docs, doc frontmatter.
pr-sweep
Use when you want to sweep all open pull requests across all repos, triage their status, run code reviews on unreviewed PRs, merge what's ready, fix quick blockers, and produce a full status report. Trigger when the user says "check my PRs", "close out open PRs", "what's the status of my PRs", "sweep my PRs", "PR…