eve is a filesystem-first framework for building durable AI agents, with agent instructions, tools, and configuration kept in ordinary project files. It is for developers creating agents that can be inspected, extended, and operated through a conventional codebase. The catalogue add-ons support working with eve agents and their workflows.
Borrowing it
Nothing to install: this file belongs to vercel/eve. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vercel/eve/main/.agents/skills/pr-shepherd/SKILL.mdgit clone --depth 1 https://github.com/vercel/eveWrote 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/vercel/eve/pr-shepherd)<a href="https://agentmods.dev/skills/vercel/eve/pr-shepherd"><img src="https://agentmods.dev/badge/skills/vercel/eve/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.
<a href="https://agentmods.dev/skills/vercel/eve/pr-shepherd"><img src="https://agentmods.dev/badge/skills/vercel/eve/pr-shepherd.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 | $0.00093 | $0.02726 |
| Opus 5.5 | $0.00037 | $0.01090 |
| Sonnet 5.5 | $0.00019 | $0.00545 |
| Haiku 4.5 | $0.00009 | $0.00273 |
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 10d 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR shepherd
Start after the first implementation is complete and checked locally. Finish when the PR has no unresolved review threads, no unanswered comments, and green CI on the latest head commit, and it is merged or set to auto-merge.
Open the PR first. Review bots and teammates comment while the rest of the work runs, so an early PR gets more feedback in each round.
1. Open the PR
- Make sure the branch is committed with
git commit -sand that commits are signed (seeAGENTS.md). Add a changeset if the change touches the publishedevepackage. - Run the fast checks from
AGENTS.md:pnpm fmt,pnpm lint,pnpm typecheck, plus the narrowest relevant unit tests. - Push the branch, then open the PR. Use the
gh-pr-descriptionskill for the body and pass it with--body-file. Open it ready for review, not as a draft, unless the user asks for a draft. - Record the PR number. Every later step uses it.
If a PR already exists for the branch (gh pr view --json number,url), reuse it.
2. Fresh-context review
Spawn one reviewer subagent with no conversation history. Give it the PR number and the branch, not your reasoning. A fresh reviewer catches what the author explains away. Use a prompt like this one:
Review PR # in this repository (
gh pr view <n>,gh pr diff <n>). ReadAGENTS.mdfirst and apply its coding, security, testing, docs, and changeset rules. Read surrounding code as needed to verify behavior. Do not edit files. Report findings ordered by severity (critical, important, minor). For each finding, give the file and line, the concrete failure or risk, and a suggested fix. Say plainly when you find nothing critical.
While the reviewer runs, you can already collect PR comments (step 3).
Triage the findings yourself. Verify each one against the code before you act.
- Fix: correctness bugs, races, security or data-loss risks, broken public behavior or docs, missing tests for changed behavior, a missing changeset, and invariant violations.
- Skip: style nits, speculative refactors, and scope creep. Mention notable skipped items to the user in the final report.
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.
- 10d ago First seen · 247 lines · 93 tokens per session scan A b8da47f3c6eb
pr-shepherd is a skill published in the GitHub repository vercel/eve (5,720 stars, last pushed today), licensed Apache-2.0. It adds 93 tokens to every session and 2,726 once invoked, about $0.0004 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 2026-10-20.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
review-triage-phase
Produces canonical review actions from fetched review state and renders action markdown. Use when the user wants only triage/action-planning for the review-framework workflow.
pr-address-comments-all
Address GitHub PR review comments on one or more PRs in parallel, each in its own git worktree on the PR's branch, reusing the pr-address-comments procedure. Auto-starts (look up PRs, create worktrees, fetch comments), then pauses to show a per-PR addressing plan for approval; after approval each PR is handled by a…
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
triage-contributor-pr
Triage open pull requests from external contributors to prisma/orm and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming contributor PRs, to decide whether a fork PR is safe to run CI on, to check whether a PR is in scope for its version…