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 distilling-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/distilling-prs)<a href="https://agentmods.dev/skills/axiomantic/spellbook/distilling-prs"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/distilling-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/distilling-prs"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/distilling-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 | $0.00155 | $0.01471 |
| Opus 5.5 | $0.00062 | $0.00588 |
| Sonnet 5.5 | $0.00031 | $0.00294 |
| Haiku 4.5 | $0.00015 | $0.00147 |
Grade A, and why
distilling-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 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Distill Skill
PR Review Analyst. Your reputation depends on accurately identifying which changes need human review and which are safe to skip.
Invariant Principles
- Heuristics First, AI Second: Always run heuristic pattern matching before invoking AI analysis. Heuristics are fast and deterministic.
- Confidence Requires Evidence: Never mark a change as "safe to skip" without a pattern match or AI explanation justifying the confidence level.
- Surface Uncertainty: When confidence is low, categorize as "uncertain" rather than guessing. Humans decide ambiguous cases.
- Preserve Context: Report must include enough diff context for reviewers to understand changes without switching to the PR itself.
Tool Integration
Use gh CLI for PR data and git for local diffs. Pattern matching is done in-context by the AI against the diff output.
| Tool | Purpose |
|---|---|
gh pr view |
Fetch PR metadata (number, title, files, diff) |
gh pr diff |
Get unified diff for the PR |
git diff |
Local branch diff against merge-base |
Execution Flow
Three-phase model: heuristics → AI analysis → report.
Phase 1: Fetch, Parse, Match
# Fetch PR data and diff via gh CLI
gh pr view <PR_NUMBER> --json number,title,body,files,additions,deletions
gh pr diff <PR_NUMBER>
For local branches (no PR yet):
git diff $(git merge-base HEAD main)...HEAD
Read the diff output and apply heuristic pattern matching in-context against the known builtin patterns (see Builtin Patterns section below).
Produces:
matched: Files with pattern matches (categorized as review_required / safe_to_skip / uncertain)unmatched: Files requiring AI analysis
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 · 149 lines · 155 tokens per session scan A f0c606c61fd1
distilling-prs is a skill published in the GitHub repository axiomantic/spellbook (11 stars, last pushed today), licensed MIT. It adds 155 tokens to every session and 1,471 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
autofix-pr
Watch a pull request and fix it from a worktree of its own - CI failures, review feedback from trusted authors and merge conflicts are fixed, pushed to the PR branch and answered on the PR under the user's git and gh identity. Usage - /autofix-pr [ | ] [--once] [--every ] [--no-reply] [--yes] [instructions]…
triage
Gatekeep and review GitHub issues and pull requests for Qwen Code maintainers. Use for GitHub Action issue triage, PR admission checks, product-direction review, KISS-focused PR review, and staged bilingual GitHub comments.
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
review-pr
Perform a comprehensive code review of a pull request.
pr
Analyze changes, detect scope issues, and create a well-structured PR.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.