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 agentmods add skills/rsenna/rs-agent-plugin/pull-request-processnpx skills add rsenna/rs-agent-plugin --skill pull-request-processgit clone --depth 1 https://github.com/rsenna/rs-agent-pluginWhat 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 | $0.00079 | $0.03633 |
| Opus 5 | $0.00039 | $0.01817 |
| Sonnet 5 | $0.00016 | $0.00727 |
| Haiku 4.5 | $0.00008 | $0.00363 |
Grade A, and why
pull-request-process 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pull Request Process
The repeatable, safe way to ship a change: branch (in its own git worktree,
never the shared checkout) → run the project's quality gate → push without
ever touching main → open a PR → stop (never merge) → work each review
thread. This is a building block other skills call (fix-mapped-issue
follows it for "till the issue is fixed").
The git/gh plumbing is in pr.sh, at ${CLAUDE_PLUGIN_ROOT}/skills/pull-request-process/pr.sh.
It is language-agnostic and does not run the quality gate — you do, per the project's docs.
Agent identity, not the personal one
Every gh call and every commit pr.sh makes uses a dedicated agent
identity (GHUB_AGENT_PATC/GHUB_AGENT_USERNAME/GHUB_AGENT_EMAIL,
sourced fresh from Doppler on every invocation — see pr.sh's own header
comment for the env vars that control which Doppler project/config), never
whatever personal gh auth account or global git identity happens to be
ambient. This isn't optional or best-effort: every subcommand dies loudly if
those secrets aren't reachable, rather than silently falling back to the
ambient identity — that silent fallback is exactly what leaked a personal
GitHub account into commits and PR comments before this existed. Commit
identity is scoped to just the task's own worktree (via git's
--worktree-level config), so it never touches the shared checkout's own
identity.
Never call gh directly for anything PR-related (gh pr comment,
gh pr create, gh api .../comments, etc.) — even for one-off actions that
feel too small to bother with pr.sh. A direct gh call rides whatever
gh auth happens to be ambient (your personal account, if you're logged in
locally), silently reintroducing the exact leak this identity enforcement exists to
prevent. Every PR interaction has a pr.sh subcommand: opening (open), a
general/top-level comment (comment), correcting one (comment-delete), a
threaded reply (reply), reading review state (threads, reviews). If a
PR action you need has no subcommand yet, that's a gap in pr.sh to fix —
add the subcommand rather than reaching for raw gh.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 261 lines · 79 tokens per session scan A a1d7ef8a6b38
pull-request-process is a skill published in the GitHub repository rsenna/rs-agent-plugin (2 stars, last pushed 2d ago), licensed MIT. It adds 79 tokens to every session and 3,633 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…