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.
npx skills add GuitarAlchemist/ga --skill grade-last-prgit clone --depth 1 https://github.com/GuitarAlchemist/gaWrote 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/guitaralchemist/ga/grade-last-pr)<a href="https://agentmods.dev/skills/guitaralchemist/ga/grade-last-pr"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/grade-last-pr/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/guitaralchemist/ga/grade-last-pr"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/grade-last-pr.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 | $0.00109 | $0.05244 |
| Opus 5.5 | $0.00044 | $0.02098 |
| Sonnet 5.5 | $0.00022 | $0.01049 |
| Haiku 4.5 | $0.00011 | $0.00524 |
Grade A, and why
grade-last-pr 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 — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/grade-last-pr
Grades the last merged PR on the current branch's upstream against the goal the author stated. Outputs a JSON grade card + a terminal summary.
Part of item #5 in docs/plans/2026-05-23-arch-harness-engineering-adoption-plan.md — "Cybernetic governance loops". Today, an agent declares "done" and that's the end of the loop. This skill closes the loop by re-reading the intent after merge and comparing it to the diff.
When to run
- Immediately after a PR merges to main — fresh memory, clean diff.
- Inside the post-merge smoke action (once item #4 lands, this skill can be invoked from CI as a follow-up step — but works standalone today).
- Spot-checking an agent's work — pick any merge SHA and grade it.
Do NOT invoke for unmerged PRs (the diff isn't stable yet — use /octo:review instead) or for revert commits (use /learnings to capture the regression).
How to run
1. Resolve the last merged PR
# Latest merge on this branch
git log -1 --format='%H %s'
# Cross-check against gh's view of merged PRs
gh pr list --state merged --limit 1 --json number,title,mergeCommit,mergedAt,headRefName
The merge SHA from git log should equal mergeCommit.oid from gh. If they disagree, the local branch is ahead of what gh sees — git fetch origin and retry, or pass an explicit PR number as the argument (/grade-last-pr 308).
Squash-merge convention means HEAD is the merged commit itself (one commit per PR). For merge-commit PRs the same logic still works; git show HEAD --stat reports the merge.
2. Capture the stated intent
gh pr view <num> --json title,body,number,mergedAt,mergeCommit,headRefName,author
The stated intent is title plus the ## Summary section of body (the first ## block, up to the next ##). If the body has no ## Summary, fall back to the title and flag intent_section_missing in reasons.
Skip everything below ## Test plan — that's how the PR was verified, not what it was for.
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 · 315 lines · 109 tokens per session scan A c76627862b54
grade-last-pr is a skill published in the GitHub repository GuitarAlchemist/ga (2 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 5,244 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 2026-08-31.
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"…
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…
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…
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…