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 farhan0167/cv-claw --skill pr-messagegit clone --depth 1 https://github.com/farhan0167/cv-clawWrote 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/farhan0167/cv-claw/pr-message)<a href="https://agentmods.dev/skills/farhan0167/cv-claw/pr-message"><img src="https://agentmods.dev/badge/skills/farhan0167/cv-claw/pr-message/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/farhan0167/cv-claw/pr-message"><img src="https://agentmods.dev/badge/skills/farhan0167/cv-claw/pr-message.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 | $0.00074 | $0.01668 |
| Opus 5.5 | $0.00030 | $0.00667 |
| Sonnet 5.5 | $0.00015 | $0.00334 |
| Haiku 4.5 | $0.00007 | $0.00167 |
Grade A, and why
pr-message 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pr-message
Draft a PR message for merging the current branch into main and hand
the user a single fenced Markdown block they can paste into the GitHub
UI or into gh pr create --body-file -.
This skill is repo-local to py-cv-claw. It does not call gh and
does not open or edit PRs.
Defaults
- base =
main - head = the current branch (typically
dev; whatevergit rev-parse --abbrev-ref HEADreturns)
Print what you inferred at the top of your reply. Do not ask the user
to confirm base/head unless head is main itself (in which case stop
and ask — there's nothing to merge).
Procedure
-
Discover scope. Run these in parallel and read the results:
git rev-parse --abbrev-ref HEAD— confirm head branch.git log --oneline main..HEAD— commits on the branch.git diff main...HEAD --stat— file-level shape (note the triple-dot: changes on HEAD relative to the merge base, ignoring work added tomainsince the branch diverged).git diff main...HEAD— read enough of the actual diff to verify commit messages tell the truth. Commits sometimes mis-describe their scope; the diff is ground truth.
-
Sanity-check the state. Stop and tell the user (don't draft) when any of these hold:
git log main..HEADis empty — no commits to describe.- Head branch is
main. - The branch contains merge commits from
mainthat muddy the diff. Offer: "Want me to describe only commits authored on this branch (git log main..HEAD --no-merges), or include the merges?"
-
Decide whether to ask for framing. Ask the user before drafting only when:
- The diff spans clearly unrelated themes and the commit titles don't unify them (e.g. one commit is a dep bump, another is an unrelated feature, no shared narrative).
- The diff is large (>~30 changed files) and commits are terse / generic.
Otherwise: draft silently. Most branches in this repo are tightly themed — don't manufacture ambiguity.
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 · 168 lines · 74 tokens per session scan A ffb719b5b26b
pr-message is a skill published in the GitHub repository farhan0167/cv-claw (4 stars, last pushed 5mo ago), licensed MIT. It adds 74 tokens to every session and 1,668 once invoked, about $0.0003 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
atmos-git
Atmos Git and GitOps: git.repositories, clone/pull/status/diff/commit/push/clean, local Git hook shims and hook env vars, signed commits, managed workdirs, fork-PR trust gate (clone gate and posting gate), and auth via identities or github/sts.
pr-squash-message
Generate one short Conventional Commits squash message describing only the net diff between the PR's base and head, set its header as the PR title, validate it with the repository's commitlint and both copy its description to the clipboard and display it, when asked for a squash message. Works in any Scenario…
git-workflow
Guided git workflows: prepare PRs, clean up branches, resolve merge conflicts, handle monorepo tags, squash-and-merge patterns. Use when asked to prepare a PR, clean branches, resolve conflicts, or tag a release.
conventional-commit
Conventional Commit - Generate Conventional Commits 1.0.0 compliant messages. MANDATORY for all git commits. Invoke when user says 'commit', 'commit this', or asks to commit code.
setup-caliber
Sets up Caliber for automatic AI agent context sync. Installs pre-commit hooks so CLAUDE.md, Cursor rules, and Copilot instructions update automatically on every commit. Use when Caliber hooks are not yet installed or when the user asks about keeping agent configs in sync.
private-secret-scanning
Local Gitleaks scans for staged changes, push ranges, and full history in private repos, with redacted reports. Use to block committed secrets without GitHub Secret Protection.