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 agentmods add skills/nrdxp/predicate/git-reviewnpx skills add nrdxp/predicate --skill git-reviewgit clone --depth 1 https://github.com/nrdxp/predicateWhat 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 | $0.00051 | $0.00829 |
| Opus 5 | $0.00026 | $0.00415 |
| Sonnet 5 | $0.00010 | $0.00166 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
git-review 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 2d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Review Workflow
A structured approach to reviewing change history with an explicit purpose. Never browse history aimlessly — always state what you're looking for.
Adversarial path anchor. This lens is invoked on the Verification Dual's adversarial path (rules.md §2 Invariant 1): when no deterministic evaluator can close a change-coherence condition, context-free agents using this protocol supply the decorrelated review. See skills/refine/SKILL.md AUDIT §"Sibling Skills Consultation" for the wiring point.
Entry: State Your Purpose
Before reviewing history, declare what you're investigating — state your purpose and scope (commits, timeframe, file path, or keyword).
Examples:
- "Trace how the auth module evolved before modifying it"
- "Find where the API contract changed and whether it was justified"
- "Locate commits related to the parsing bug we're debugging"
Modes
SUMMARY — Get the lay of the land
git log --oneline -n 20 # Recent commits
git log --oneline --since="1 week ago" # Time-bounded
git shortlog -sn --since="1 month ago" # By author
SEARCH — Find commits relevant to your purpose
git log --grep="keyword" --oneline # Message search
git log --all --oneline -- "path/to/file" # File history
git log -S "function_name" --oneline # Code change search
EXPAND — Examine specific commits
git show <hash> # Full commit details
git diff <hash>^..<hash> # Diff only
git show <hash> --stat # Changed files summary
Review Procedure
- STATE PURPOSE — What are you trying to trace or verify?
- SUMMARY — Scan relevant history for context
- SEARCH — Narrow to commits relevant to your purpose
- EXPAND — Examine suspicious or unclear commits
- ASSESS — Apply the coherence checklist
Coherence Checklist
When examining a commit, assess:
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.
- 2d ago First seen · 115 lines · 51 tokens per session scan A 24e43a93cc61
git-review is a skill published in the GitHub repository nrdxp/predicate (10 stars, last pushed 8d ago), licensed MIT. It adds 51 tokens to every session and 829 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…