Borrowing it
Nothing to install: this file belongs to atheurer/agentic-perf. 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/atheurer/agentic-perf/main/.agents/skills/agentic-perf-pr-cycle/SKILL.mdgit clone --depth 1 https://github.com/atheurer/agentic-perfWrote 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/atheurer/agentic-perf/agentic-perf-pr-cycle)<a href="https://agentmods.dev/skills/atheurer/agentic-perf/agentic-perf-pr-cycle"><img src="https://agentmods.dev/badge/skills/atheurer/agentic-perf/agentic-perf-pr-cycle/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/atheurer/agentic-perf/agentic-perf-pr-cycle"><img src="https://agentmods.dev/badge/skills/atheurer/agentic-perf/agentic-perf-pr-cycle.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 | $0.00039 | $0.01204 |
| Opus 5.5 | $0.00016 | $0.00482 |
| Sonnet 5.5 | $0.00008 | $0.00241 |
| Haiku 4.5 | $0.00004 | $0.00120 |
Grade A, and why
agentic-perf-pr-cycle 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 today.
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic-perf PR cycle
Use this skill to work through an existing pull request from initial review to final CI checks. For the one-at-a-time backlog workflow, read references/backlog-pr-cycle.md. For a new implementation, use the issue-first development workflow in agentic-perf-orchestration, then return here for the PR review and landing steps.
Repository guidance is authoritative for current commands and policy. Read AGENTS.md, CONTRIBUTING.md, docs/reviewing.md, and the relevant audit or testing docs for the paths under review. Do not copy mutable project details into this skill when a repository document already owns them.
Review, fix, and revalidate
- Verify the clean base checkout, PR base and head SHAs, author, changed files, commits, and check state. Record the expected remote head. Use an isolated worktree for source review; do not bring unrelated checkout changes into it.
- If the PR is based on stale
main, bring the exact PR head onto the currentorigin/mainin a fresh worktree. Resolve conflicts deliberately and inspect the complete resulting diff. Stop before pushing if the remote PR head has changed. - Review the full diff independently from its implementation. Trace changed contracts through their producers, consumers, schemas, prompts, and tests. Apply docs/reviewing.md and the relevant audit policies.
- Classify each finding as PR-introduced or review-discovered follow-up. Fix material PR-introduced correctness, security, or behavior findings before push. Track pre-existing follow-ups separately; create a focused issue when that is appropriate for the workflow and link it to the PR. Do not describe a pre-existing defect as a regression.
- After every implementation or generated-file change, format the changed files before testing and inspect the complete diff. Repeat the independent review and every affected validation step after review-driven fixes.
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.
- today First seen · 98 lines · 39 tokens per session scan A cb1ddbb496c9
agentic-perf-pr-cycle is a skill published in the GitHub repository atheurer/agentic-perf (6 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 1,204 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 2026-10-29.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…