contributor-pr

contributor-pr is a skill for Claude Code, Codex from Fighter90/career-ops-ui. It costs 65 tokens per session (1,349 once invoked), scanned A, original, MIT.

A workflow for reviewing, merging, and releasing pull requests from outside contributors in web-ui. A pull request is a proposed code change, and a fork is a contributor’s separate copy of the repository.

In plain words
What is it for?
Reading full contributor diffs, reviewing security and LLM-related changes, running local verification, merging with explicit approval, and updating contributor lists in project documentation and cvstart.org.
Why use it?
It adds checks for untrusted or unverified external code, especially where normal fork-based CI does not run automatically.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/fighter90/career-ops-ui/contributor-pr
Any agent
npx skills add Fighter90/career-ops-ui --skill contributor-pr
Clone the repo
git clone --depth 1 https://github.com/Fighter90/career-ops-ui

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for contributor-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/fighter90/career-ops-ui/contributor-pr.svg)](https://agentmods.dev/skills/fighter90/career-ops-ui/contributor-pr)
Your own site
<a href="https://agentmods.dev/skills/fighter90/career-ops-ui/contributor-pr"><img src="https://agentmods.dev/badge/skills/fighter90/career-ops-ui/contributor-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,349 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00065 $0.01349
Opus 5 $0.00032 $0.00674
Sonnet 5 $0.00013 $0.00270
Haiku 4.5 $0.00006 $0.00135

Measured 5d ago against content hash b2770d6232eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

contributor-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 5d 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.

.claude/skills/contributor-pr/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

contributor-pr — external PR intake pipeline

Proven on v1.125.2 (PRs #144/#145 by @Alien10140 — Gemini defaults + the headless deep-prompt 502 fix). External code gets a stricter path than our own branches: fork CI does not auto-run, review claims are verified empirically, and merges need explicit user authorization.

Phase 1 — Review (local runs ARE the CI gate)

  1. Fork PRs from first-time contributors show "no checks reported" — GitHub Actions waits for maintainer approval. Don't chase it; the local full-suite run below substitutes, and push-CI on main re-validates after merge. (Approving runs via gh api …/actions/runs/<id>/approve and gh pr merge are both classifier-blocked for external PRs — when blocked, STOP and hand the user the exact commands; never work around.)
  2. git fetch origin pull/<n>/head:pr-<n> and read the FULL diff. Extra scrutiny on LLM surfaces (prompts.mjs, routes/llm.mjs), sanitizers, any new ingress, and i18n snapshot regeneration (dup keys / glosses). Check the contributor's tests honor CI isolation (dynamic imports in before(), CAREER_OPS_ROOT mktemp — the paths-once rule).
  3. Verify factual claims against live sources, never training data. v1.125.2 lesson: an AI review called gemini-3.6-flash "fabricated" as a BLOCKER; fetching https://ai.google.dev/gemini-api/docs/models proved the contributor right (3.6-flash Stable, 2.0-flash shut down). Model ids, API shapes, deprecations → WebFetch the official docs.
  4. Run the full suite on EACH pr-branch: npm test, capture the exit code directly (never pipe to grep). Record per-branch counts.
  5. Before merging, re-check gh pr view <n> --json headRefOid still equals the SHA you reviewed.

Phase 2 — Merge

  • Needs the user's explicit go for THESE PRs (standing "merge all branches" does not auto-extend to external code; the classifier enforces this).
  • gh pr merge <n> --squash --delete-branch, oldest first; then git checkout main as its OWN command, then git pull (a checkout inside a blocked compound command silently never runs; v1.125.2: a README commit landed on the local pr-144 branch that way and had to be cherry-picked to main).
  • Full suite on merged main.

Read the full file on GitHub · 93 lines

Changes

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.

  1. 5d ago First seen · 93 lines · 65 tokens per session scan A b2770d6232eb

Subscribe to this mod's changes

contributor-pr is a skill published in the GitHub repository Fighter90/career-ops-ui (61 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 1,349 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 2026-08-30.

Related

Other skills, from other repositories

version-release

Choose and apply the correct semantic version bump for this repository. Use for every user-visible release, before merge when a change set should ship as patch, minor, or major, and whenever package/plugin/desktop version metadata must stay synchronized.

hoangsonww/Claude-Code-Agent-Monitor · 50 tokens

release-guard

Run release-readiness checks for this repository. Use when validating docs, scripts, verification coverage, and operational safety before merge or release.

hoangsonww/Claude-Code-Agent-Monitor · 31 tokens

pull-request

Use this whenever the user asks to "open a PR", "ship this", "create the pull request", "make a PR", or once a feature/fix is verified and ready to push. Full lifecycle: branch → commit (commitizen) → issue → draft PR → CI → ready → autonomous monitor loop (fix comments, resolve threads, iterate until CI green + zero…

pierreb-devkit/Node · 113 tokens

ship

MANUAL TRIGGER ONLY: invoke only when user types /ship. Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", or "merge and push". Proactively suggest when the user says code is…

act-sdk/act-sdk-js · 86 tokens

document-release

MANUAL TRIGGER ONLY: invoke only when user types /document-release. Post-ship documentation update. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION. Use when asked to…

act-sdk/act-sdk-js · 107 tokens

agent-release-swarm

Agent skill for release-swarm - invoke with $agent-release-swarm.

ruvnet/ruflo · 19 tokens