ga: Skill for Claude Code

.claude/skills/grade-last-pr/SKILL.md

grade-last-pr is a skill for Claude Code from GuitarAlchemist/ga. It costs 109 tokens per session (5,244 once invoked), scanned A, original, MIT.

A post-merge review that compares a merged pull request, a proposed code change, with its stated goal and the code that actually landed. It also considers specialist review comments and certain automated warnings.

In plain words
What is it for?
Use it to grade the latest merged pull request for alignment between its purpose and implementation.
Why use it?
It shows whether the delivered change matched its original intent after the merge is complete.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions Codex.

This is GuitarAlchemist/ga's own configuration. It tells Claude Code how to work on ga itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ga configures →

Reuse

Borrowing it

Nothing to install: this file belongs to GuitarAlchemist/ga. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/GuitarAlchemist/ga/main/.claude/skills/grade-last-pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/GuitarAlchemist/ga

Made for: Claude Code.

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 grade-last-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/guitaralchemist/ga/grade-last-pr/github.svg)](https://agentmods.dev/skills/guitaralchemist/ga/grade-last-pr)
Your own site
<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.

agentmods 80×15 button for grade-last-pr

Your own site · 80×15
<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>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,244 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 $0.00109 $0.05244
Opus 5 $0.00055 $0.02622
Sonnet 5 $0.00022 $0.01049
Haiku 4.5 $0.00011 $0.00524

Measured 9d ago against content hash c76627862b54, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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 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.

.claude/skills/grade-last-pr/SKILL.md · 315 lines

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.

Read the full file on GitHub · 315 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 · 315 lines · 109 tokens per session scan A c76627862b54

Subscribe to this mod's changes

grade-last-pr is a skill published in the GitHub repository GuitarAlchemist/ga (2 stars, last pushed today), licensed MIT. It adds 109 tokens to every session and 5,244 once invoked, about $0.0005 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.