Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/OpenCoven/covennpx agentmods add skills/opencoven/coven/pr-agentWrote 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/opencoven/coven/pr-agent)<a href="https://agentmods.dev/skills/opencoven/coven/pr-agent"><img src="https://agentmods.dev/badge/skills/opencoven/coven/pr-agent/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/opencoven/coven/pr-agent"><img src="https://agentmods.dev/badge/skills/opencoven/coven/pr-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.00501 |
| Opus 5.5 | $0.00017 | $0.00200 |
| Sonnet 5.5 | $0.00008 | $0.00100 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
pr-agent 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 1mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coven PR Readiness Agent
This skill prepares OpenCoven pull requests for maintainer review. It does not own merge authority; it produces the readiness packet a maintainer or another agent can trust.
Readiness Packet
Build the PR around five concrete sections:
- Context: user problem, linked issue, constraints, and prior decisions.
- Implementation: files changed, behavioral surface, and compatibility notes.
- Verification: commands run, manual checks, skipped checks, and exact failures.
- Risk and Rollback: regression risk, data/security impact, and rollback path.
- Agent Handoff: current state, follow-ups, and known gaps.
Context Bundle
Before drafting or updating a PR, gather:
git status --shortgit diff --stat- Linked issue or product request
- Changed docs, tests, scripts, and Rust crates
- Any local proof output needed by the PR body
Do not create or update a PR until the context bundle is internally consistent and unrelated dirty work is identified.
Template Assembly
Use .github/pull_request_template.md as the output contract. Keep headings
stable so automation and reviewers can scan the packet quickly.
The PR body must include:
Closes #when there is a linked issue- Summary and files changed
- Implementation notes with user-visible behavior
- Verification matrix with exact commands
- Risk level and rollback plan
- Agent handoff notes for remaining work
Verification Matrix
Default repository gates:
cargo fmt --check
cargo clippy --workspace --all-targets -- -D warnings
cargo test --workspace --locked
python3 scripts/check-secrets.py
For docs-only or script-only changes, record the narrower focused checks and say why the full gate was not necessary.
Guardrails
- Preserve unrelated dirty work.
- Prefer the smallest complete PR.
- Separate required fixes from optional follow-ups.
- Call out skipped checks explicitly.
- Do not create or update a PR until verification evidence is present or the gap is named.
What ships with it
2 files 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.
- 1mo ago First seen · 76 lines · 42 tokens per session scan A d2a0b1065f1c
pr-agent is a skill published in the GitHub repository OpenCoven/coven (73 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 501 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
pr-comment
Answer a maintainer's question about an open PR with concrete, code-cited evidence. The PR-side counterpart to issue-comment — for questions tied to the diff, not a full review.
github
Inspect repositories, PRs, issues, and CI workflows.
address_pr_comments
First, check the branch {{ BRANCHNAME }} and read the diff against the main branch to understand the purpose.
pr-triage
PR triage: audit open PRs, deep review selected ones, draft and post review comments. Args: "all" to review all, PR numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.