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 axiomantic/spellbook --skill reviewing-prsgit clone --depth 1 https://github.com/axiomantic/spellbookWrote 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/axiomantic/spellbook/reviewing-prs)<a href="https://agentmods.dev/skills/axiomantic/spellbook/reviewing-prs"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/reviewing-prs/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/axiomantic/spellbook/reviewing-prs"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/reviewing-prs.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 | $0.00105 | $0.01475 |
| Opus 5 | $0.00053 | $0.00737 |
| Sonnet 5 | $0.00021 | $0.00295 |
| Haiku 4.5 | $0.00011 | $0.00147 |
Grade A, and why
reviewing-prs 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.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewing PRs Safely
Invariant Principles
- Determine review_source First: Never dispatch a PR review subagent without computing
review_source. No exceptions. - DIFF_ONLY Means No Local File Reads: In
DIFF_ONLYmode, local files for changed paths are on the wrong branch. Reading them produces wrong verdicts. - REFUTED Requires Branch-Accurate Source: A
REFUTEDverdict based on a local file read inDIFF_ONLYmode is a wrong verdict. Mark itINCONCLUSIVEor[NEEDS VERIFICATION]. - Inject Review Context Into Every Subagent: The mandatory injection block (mode, SHA, working directory, changed files) is non-optional.
The Wrong-Branch Failure
When reviewing a PR via diff, local files are on a different branch. Reading them produces silently wrong results:
- PR-introduced changes appear absent (local has old code)
- Real bugs get declared "not present" → false REFUTED verdicts
- Findings carry high confidence in factually wrong conclusions
This is a structural failure: the agent reads the wrong version of the file.
Review Source Decision
Before dispatching any code review subagent, determine review_source:
PR_HEAD_SHA=$(gh pr view <PR_NUMBER> --json headRefOid --jq '.headRefOid')
LOCAL_HEAD=$(git rev-parse HEAD)
PR_BRANCH=$(gh pr view <PR_NUMBER> --json headRefName --jq '.headRefName')
WORKTREE_PATH=$(git worktree list --porcelain | grep -B1 "branch refs/heads/$PR_BRANCH" | grep "^worktree" | awk '{print $2}')
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.
- 9d ago First seen · 132 lines · 105 tokens per session scan A 1b636bd4c831
reviewing-prs is a skill published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 105 tokens to every session and 1,475 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 2026-09-03.
Other skills, from other repositories
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
ship
Use when code is ready to ship — creates PRs, merges, deploys, and verifies. Handles the full PR-to-production pipeline. Triggers on /ship.
release-readiness
Use after review/qa/security/license-audit/privacy-check to compose a release decision before /ship. Returns OK only when all required upstream evidence is present and clean. Triggers on /release-readiness.
init
Turn on Rekal memory in the current repository by running rekal init. Use when the user asks to initialize or set up Rekal here, or when a rekal command reported the repository is not initialized. Once per repository. Do not offer this merely because a repo lacks a .rekal/ store — most repos do not want one.