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 MongLong0214/commitlore --skill commitlore-setupgit clone --depth 1 https://github.com/MongLong0214/commitloreWrote 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/monglong0214/commitlore/commitlore-setup)<a href="https://agentmods.dev/skills/monglong0214/commitlore/commitlore-setup"><img src="https://agentmods.dev/badge/skills/monglong0214/commitlore/commitlore-setup/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/monglong0214/commitlore/commitlore-setup"><img src="https://agentmods.dev/badge/skills/monglong0214/commitlore/commitlore-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00129 | $0.01508 |
| Opus 5.5 | $0.00052 | $0.00603 |
| Sonnet 5.5 | $0.00026 | $0.00302 |
| Haiku 4.5 | $0.00013 | $0.00151 |
Grade A, and why
commitlore-setup 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 1mo 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CommitLore setup
Every command below is the commitlore CLI, which arrives with install.sh /
install.ps1. The Claude Code plugin ships the MCP server, the pre-edit hook
and these skills, and puts nothing on PATH — where commitlore is not found,
node <plugin-checkout>/dist/commitlore.mjs takes the same arguments.
Shortcut for a repository that just needs wiring up, nothing broken to diagnose:
commitlore init runs steps 2-4 below (hooks install, index --rebuild, then
doctor --fix as a final check) in one command, reports what it did and what it
could not, and is safe to re-run. Use the four steps below one at a time when
something specific looks broken and you want to isolate which piece.
Four checks, in order. Each one is independent and re-runnable — running any of them twice on an already-configured repo is a no-op, not an error.
1. Diagnose
commitlore doctor
Reports ok, warn, or skipped for: whether the origin remote fetches
refs/notes/commitlore (records that live only in the notes mirror never
reach a teammate whose fetch config omits that ref), whether there is a local
notes mirror to push, whether the commit-msg hook is installed, and whether
the local git build parses trailers the way the spec expects. warn lines
carry their own fix directly underneath — read that before doing anything
else. Example, run against a repo that has a remote but nothing else set up:
warn notes fetch refspec — origin does not fetch refs/notes/commitlore, so records pushed by others stay invisible here
fix: git config --add remote.origin.fetch '+refs/notes/commitlore:refs/notes/commitlore'
ok notes push — no local mirror yet — nothing to push (git push origin refs/notes/commitlore, once there is)
warn commit-msg hook — no commit-msg hook at .git/hooks/commit-msg
fix: commitlore hooks install
ok git interpret-trailers — git version 2.50.1 (Apple Git-155) parses trailers as the spec expects
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.
- 1mo ago First seen · 132 lines · 129 tokens per session scan A f821d6dcc532
commitlore-setup is a skill published in the GitHub repository MongLong0214/commitlore (18 stars, last pushed today), licensed MIT. It adds 129 tokens to every session and 1,508 once invoked, about $0.0005 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
fix-pr-commit-titles
Bulk-rewrite commit titles on a PR branch to match [LKPR-N] format using filter-branch — avoids per-commit hook re-runs.
github-pr-workflow
GitHub PR lifecycle: branch, commit, open, CI, merge.
proposal-filing
File a new Lorekeeper proposal ticket — create markdown, create GitHub issue, commit, push. Use when requesting a new feature, filing a bug, or submitting a product idea.
commit-convention
Git commit convention for Lorekeeper — enforced by commit-msg hook. Covers author identity, ticket tags, and message format for both PM (Akane) and Dev roles.
git-ops
Close out a local coding task on the bound daemon — stage, commit, branch, merge, push via cloud git — and when a merge conflicts, STOP and escalate with the file list instead of auto-resolving. Push reaches only the bare replica; prod-triggering tags are refused.
pre-pr
Prepare a Honcho change for a pull request to plastic-labs/honcho. Invoke before opening a PR, when drafting a PR body, when asked if a branch is PR-ready, or when filling the pull request template. Checks the linked issue, required tests and docs, then writes Description / Proofs / Fixes.