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 bengous/claude-code-plugins --skill prgit clone --depth 1 https://github.com/bengous/claude-code-pluginsWrote 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/bengous/claude-code-plugins/pr)<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/pr"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/pr/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/bengous/claude-code-plugins/pr"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/pr.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 | $0.00051 | $0.01709 |
| Opus 5 | $0.00026 | $0.00855 |
| Sonnet 5 | $0.00010 | $0.00342 |
| Haiku 4.5 | $0.00005 | $0.00171 |
Grade A, and why
pr 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR
A PR body is a review brief. Its reader is a different agent, in a fresh session, with the diff and the tools. The body says why the change exists, where to look first, and what was already checked. The body proves; the reviewer judges.
Input
$ARGUMENTS
--dry-run: no push, no publish; print the title, the base, the body and the attachments instead.- Paths ending in
.png,.jpg,.gif,.mp4,.mov: files to attach. Alt text may follow the path after#. - The rest: what the reviewer should know, kept as facts in the body.
- Empty: everything comes from the branch.
Protocol
- Branch.
git branch --show-current. Ondev,main, or the repo's default branch: stop, showgit status --short, ask for a branch name. Uncommitted changes: stop and say so; the commit comes first (/git:commit). - Base.
devwhenorigin/devexists, elsegh repo view --json defaultBranchRef. Without--dry-run, push withgit push -u origin HEAD. A rejected push: report it verbatim and stop; never force. - Evidence. Read before citing.
git log --oneline <base>..HEADandgit diff --stat <base>...HEAD: the size, the files.- Tests added by the branch:
git diff --stat <base>...HEAD -- '*test*'. - The issue:
Closes #Nin a commit body, else the leading number of the branch name, else none.gh issue view <n> --json title,bodywhen there is one. - When the issue has an Out of scope section: every file of
git diff --name-only <base>...HEADthat it names. - The repo's
AGENTS.mdorCLAUDE.md: the validation commands. - What ran this session, with its numbers.
- Images. A change the reader sees (a page, a view, a component, a stylesheet) gets a Before/After pair when
$ARGUMENTSgave none. The browser tool of the session captures the base state (the live page, else the base branch served) and the branch, one state per file, outside the repo. No reachable base: After alone, and the caption says so. A change with no visible result gets no image. - Body. Pick the size from step 3, fill the sections below. The title follows the convention of
git log --oneline -10. - Publish. No question before it: the skill is the guard, and a caller that wants a look first passes
--dry-run. Files the issue puts out of scope go in Ask, so the reviewer decides. Body in a temporary file outside the repo. A PR already open on the branch (gh pr view --json number,body) is edited, else one is created:
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 Changed · +8 lines 1a248cf29f67
- 6d ago First seen · 76 lines · 51 tokens per session scan A 7467e0cc6027
pr is a skill published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 1,709 once invoked, about $0.0003 per session on Opus 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 2026-09-11.
Other skills, from other repositories
work
Dispatch a tracker ticket into an isolated worktree and drive it autonomously to an open pull request, then stop for review. Pass interactive to brainstorm the ticket with a human before planning it, or a sentence of editorial direction as a rider. Use when asked to work a ticket end-to-end.
batch
Dispatch a night's batch of Todo tickets — one worktree and one pull request each — and leave a morning summary. Run explicitly; never inferred.
cleanup
Clean up after a merged pull request — return to the base branch, remove the worktree, delete the branch, sweep other stale branches and worktrees, and report tracker state. Use after a merge or whenever asked what is left over.
merge
Merge the reviewed pull request for the current branch, then hand straight off to cleanup. A sentence of editorial direction alongside the green light is read as a rider. Use when a human green-lights an open PR.
release
Verify, write the CHANGELOG, cut a version — then hand the release sequence back.
taiyi-integration
A project workflow skill for closing a TaiyiForge change and recording it in a CHANGELOG.md file. It checks review results, tests, and the state of the working tree before archiving the change.