pr-shepherd

pr-shepherd is a skill for Claude Code, Codex from dshakes/compass. It costs 101 tokens per session (1,159 once invoked), scanned A, original, MIT.

A workflow for handling open GitHub pull requests from failed checks through the merge decision. A pull request is a proposed code change, and its checks are automated tests or other validations run before merging.

In plain words
What is it for?
Use it to inspect open pull requests, diagnose failed checks, fix mechanical problems on eligible branches, verify the fixes, and report whether each request is ready to merge or needs human attention.
Why use it?
It removes the need to manually inspect every failing check and separates code defects from failures caused by infrastructure or missing settings. It also stops at the point where human approval or another decision is required.

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/dshakes/compass/pr-shepherd
Any agent
npx skills add dshakes/compass --skill pr-shepherd
Clone the repo
git clone --depth 1 https://github.com/dshakes/compass

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 pr-shepherd

README.md
[![agentmods](https://agentmods.dev/badge/skills/dshakes/compass/pr-shepherd.svg)](https://agentmods.dev/skills/dshakes/compass/pr-shepherd)
Your own site
<a href="https://agentmods.dev/skills/dshakes/compass/pr-shepherd"><img src="https://agentmods.dev/badge/skills/dshakes/compass/pr-shepherd.svg" alt="Measured on agentmods" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,159 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 $0.00101 $0.01159
Opus 5 $0.00051 $0.00580
Sonnet 5 $0.00020 $0.00232
Haiku 4.5 $0.00010 $0.00116

Measured 3d ago against content hash 37a499f04356, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-shepherd 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 3d 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/pr-shepherd/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR shepherd — the loop's handoff + verification moves, applied to PRs

A loop has five moves: discovery → handoff → verification → persistence → scheduling (see docs/20-loops.md). morning-triage is discovery — it finds work. This skill is what happens after a PR exists: no PR sits red waiting for a human to diagnose a check that a machine can read. It shepherds each open PR to exactly one of three outcomes: merged (gate satisfied + authority granted), ready-to-merge (reported), or inbox (needs a human, with the diagnosis already written).

Enumerate

gh pr list --state open --json number,title,author,isDraft,isCrossRepository,headRefName,statusCheckRollup

Skip drafts. Fail closed on forks: if isCrossRepository is true — or the field is missing from the response — the PR is read-only: diagnose and comment, never check out into a pushable worktree, never push.

Diagnose — read the check, don't guess

For each red check, read the actual failing step (gh run view <run-id> --log-failed) and classify it. The class decides the action — this is the judgment step, don't skip it:

class signature action
environmental missing secrets (Dependabot actor), runner flake, quota note it; if it recurs, fix the workflow (root cause), not the PR
mechanical drift/sync gates, lint, format, lockfile, generated files fix it on the PR branch
real defect failing tests on changed logic, security finding never auto-fix silently — comment the diagnosis on the PR, mark inbox

A failure that pattern-matches "flake" still gets its log read once. Silence is not success: a check that never ran (skipped, stuck queue) is a finding, not a pass.

Fix — mechanical only, verified before pushed

Work in a scratch worktree (git worktree add … origin/<branch>), never in the main checkout:

  1. Make the smallest fix the failing gate names (e.g. the gate says run: cp sdlc/workflows/X .github/workflows/ — run that).
  2. Run the same gate locally and watch it pass before pushing. Never push a guess.
  3. Push to the PR branch with a commit message that names the gate it satisfies.
  4. Three strikes: after 3 failed fix attempts on one PR, stop — mark it inbox with what was tried. A non-converging loop must stop spending (the resource-ceiling principle).

Read the full file on GitHub · 85 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. 3d ago First seen · 85 lines · 101 tokens per session scan A 37a499f04356

Subscribe to this mod's changes

pr-shepherd is a skill published in the GitHub repository dshakes/compass (19 stars, last pushed 9d ago), licensed MIT. It adds 101 tokens to every session and 1,159 once invoked, about $0.0005 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens