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 juxt/claude-plugins --skill prgit clone --depth 1 https://github.com/juxt/claude-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/juxt/claude-plugins/pr)<a href="https://agentmods.dev/skills/juxt/claude-plugins/pr"><img src="https://agentmods.dev/badge/skills/juxt/claude-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/juxt/claude-plugins/pr"><img src="https://agentmods.dev/badge/skills/juxt/claude-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 | $0.00130 | $0.02287 |
| Opus 5.5 | $0.00052 | $0.00915 |
| Sonnet 5.5 | $0.00026 | $0.00457 |
| Haiku 4.5 | $0.00013 | $0.00229 |
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 4d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pull Request
Interpret MUST, MUST NOT, SHOULD, SHOULD NOT, MAY, etc. per RFC 2119.
This skill owns the PR description.
Which sections the body gets comes from chalk:voice's references/palette.md; this skill covers what a PR description is for, and how it gets opened.
A PR description freezes at merge. Unlike an issue, it has no mechanism for resolving what it doesn't yet know, so it states what is now true rather than what might be — and it hands the change over rather than arguing for it.
Your readers
chalk:voice says who they are; here they are doing one of two things, and neither of them is a gate.
Any one reader is doing one of the two; you are writing for both at once, so the description MUST serve each and satisfying one is not a licence to drop the other.
A PR does get approved, but the approver is not who you write for: they hold the diff, so argument where they could just look reads as something you couldn't show.
-
Reader 1 is a peer updating their mental model, now. They need the delta, and above all the belief they hold that no longer holds. A PR is the moment the rest of the team learns the change exists, so their first question is whether it affects them. Success: the reader can tell how this affects their work, and what they believe about the system afterwards is true - the understanding is conveyed accurately and concisely.
-
Reader 2 is the same person in a year, asking why one aspect of this mattered. Success: they don't accidentally revert it, and they don't rehash from scratch a decision this description already settled.
Which path
-
Resolves an issue — the issue carries the problem, so this description MUST NOT restate it. Reference it at the top (
Resolves #N, orPart of #N) and assume the reader has read it. What this adds is how the problem shaped the implementation: the approach, the decisions, the trade-offs, the dead ends.tl;dr → What changes → Usage / migration → Consequences → Out of scope → Alternative approaches → Open questions
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.
- 4d ago Changed · +1 lines aeba55cddaec
- 11d ago Changed · +3 lines 752426bfbd4b
- 1mo ago Changed · -11 lines 3c3a052741e7
- 1mo ago Changed · +30 lines 2e99bf5906f4
- 1mo ago Changed · +3 lines 483e7c04ef5b
- 1mo ago Changed · +38 lines ab8a25014ad3
- 1mo ago Changed · +5 lines 5f32a1ae864f
- 1mo ago First seen · 90 lines · 130 tokens per session scan A e9bee19542c6
pr is a skill published in the GitHub repository juxt/claude-plugins (10 stars, last pushed yesterday), licensed MIT. It adds 130 tokens to every session and 2,287 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
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…