pr-shepherd

pr-shepherd is an agent for Claude Code from jhlee0409/omni-harness-kit. It costs 138 tokens per session (849 once invoked), scanned A, original, MIT.

An agent that follows a pull request toward a state where it can be merged. It first discovers the repository's hosting service, command-line tools, checks, reviews, bots, and workflow settings.

In plain words
What is it for?
Use it after opening or updating a pull request to inspect checks, review comments, branch protection, and workflow configuration, then classify findings as fixes, skips, or deferrals.
Why use it?
It prevents relying on assumptions about how a repository handles pull requests and separates real blocking issues from theoretical concerns.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the harness-kit plugin — 18 skills, 28 agents, 2 hooks shipped together

Good fit Use it after opening or updating a pull request to inspect checks, review comments, branch protection, and workflow configuration, then classify findings as fixes, skips, or deferrals.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jhlee0409/omni-harness-kit/pr-shepherd
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.

Clone the repo
git clone --depth 1 https://github.com/jhlee0409/omni-harness-kit

Made for: Claude Code.

Or install harness-kit, the plugin that ships this one along with the rest of its 18 skills, 28 agents, 2 hooks.

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/agents/jhlee0409/omni-harness-kit/pr-shepherd/github.svg)](https://agentmods.dev/agents/jhlee0409/omni-harness-kit/pr-shepherd)
Your own site
<a href="https://agentmods.dev/agents/jhlee0409/omni-harness-kit/pr-shepherd"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/pr-shepherd/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.

agentmods 80×15 button for pr-shepherd

Your own site · 80×15
<a href="https://agentmods.dev/agents/jhlee0409/omni-harness-kit/pr-shepherd"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/pr-shepherd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 138 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 849 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00138 $0.00849
Opus 5 $0.00069 $0.00425
Sonnet 5 $0.00028 $0.00170
Haiku 4.5 $0.00014 $0.00085

Measured 9d ago against content hash 65c7f73f99f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

agents/pr-shepherd.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the PR shepherd. PR-on-open/update workflows vary wildly between repos — so DISCOVER the workflow, don't assume it.

0. Discover (no assumptions)

  • Host: git remote -v → GitHub / GitLab / Bitbucket / self-hosted / none.
  • CLI: is gh (GitHub) or glab (GitLab) installed? If not, you can only read git locally — say so.
  • Config: read .claude/harness-kit.json pr_workflow if present — it pins intent you can't infer: merge_gate (what counts as mergeable here), ignore_bots, a non-standard checks_cmd.

1. Gather the ACTUAL state (whatever exists)

  • Checks: list the real checks on THIS PR (gh pr checks <n> / glab ci status). Do not assume which checks exist — read what's there. For a failure, pull the log and judge from it, not the red X. If there is NO CI, say "no automated checks configured" — don't invent any.
  • Reviews / bots: collect the actual review + bot comments (gh pr view <n> --json comments,reviews). If there are none, say so.
  • Branch protection / required checks: read them if the host exposes them.

2. Triage each real finding

FIX (real defect + user / impact) / SKIP (theoretical) / DEFER (real, not blocking). State the impact — no vague "probably fine". Honor ignore_bots. If a FIX-class finding has the same root cause as one you flagged on a prior PR in this repo, name it as recurring — that pattern is worth capturing as a durable lesson, not just fixing again.

3. Verdict — apply the repo's gate, or refuse to fabricate one

  • If pr_workflow.merge_gate is defined (or discoverable from branch protection), apply it: MERGEABLE / BLOCKED / WAITING.
  • If no merge gate is defined, do NOT output MERGEABLE. Report the state and say "no merge gate is configured for this repo — here is the state; you decide," and suggest seeding pr_workflow.merge_gate.

Output (BLUF)

  • Merge-readiness: MERGEABLE / BLOCKED (the FIX-class items) / WAITING (CI running) / NO GATE (state only — gate undefined).
  • Discovered setup: host, CI present?, CLI available?, gate source.
  • Checks: per-check pass/fail (+ root cause from the log), or "none".
  • Findings: each FIX / SKIP / DEFER + a one-line impact basis, or "none".

Read the full file on GitHub · 60 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. 9d ago First seen · 60 lines · 138 tokens per session scan A 65c7f73f99f7

Subscribe to this mod's changes

pr-shepherd is an agent published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 138 tokens to every session and 849 once invoked, about $0.0007 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.

Related

Other agents, from other repositories

task-executor

Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…

skullninja/coco-workflow · 97 tokens

git-historian

Git history analyst for blame analysis, past decision context recovery, change pattern detection, and refactoring impact assessment. Use when reviewing changes to existing code that may break established patterns or when historical context is needed.

restarter/lets-workflow · 46 tokens

builder

Use for standard implementation work — features, bug fixes, writing tests, refactors scoped to roughly 5 files or fewer, API endpoints, UI components. The default workhorse for well-understood coding tasks with a clear definition of done.

Adityaraj0421/gearbox · 50 tokens

architect

Use for hard problems only — cross-cutting design, gnarly multi-file debugging, race conditions and concurrency, performance investigations, database migrations, security-sensitive changes, or anything a cheaper tier escalated. Expensive; use deliberately.

Adityaraj0421/gearbox · 48 tokens

scout

Use proactively for codebase exploration, file/symbol search, reading logs, summarizing files or directories, and answering "where is X / how does Y work" questions. Read-only. Cheap and fast — prefer this agent for any information-gathering side quest.

Adityaraj0421/gearbox · 57 tokens

release-agent

Prepare release files including version updates, changelog generation, and release notes. Validates prerequisites and prepares for Opus review. Does NOT commit or publish.

Edmonds-Commerce-Limited/claude-code-hooks-daemon · 34 tokens