git-review

A structured way to inspect a project’s Git history, which records how its code changed over time. It focuses the review on a stated question instead of scanning commits without a purpose.

In plain words
What is it for?
Use it to trace how a feature evolved, find commits related to a bug, check API changes, or review commit messages and diffs.
Why use it?
It helps determine why a change was made, whether an interface changed, and whether commits form a coherent story. This can reveal context that is missing from the current files.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/nrdxp/predicate/git-review
Any agent
npx skills add nrdxp/predicate --skill git-review
Clone the repo
git clone --depth 1 https://github.com/nrdxp/predicate

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 829 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00051 $0.00829
Opus 5 $0.00026 $0.00415
Sonnet 5 $0.00010 $0.00166
Haiku 4.5 $0.00005 $0.00083

Measured 2d ago against content hash 24e43a93cc61, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

skills/git-review/SKILL.md · 115 lines

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

  1. STATE PURPOSE — What are you trying to trace or verify?
  2. SUMMARY — Scan relevant history for context
  3. SEARCH — Narrow to commits relevant to your purpose
  4. EXPAND — Examine suspicious or unclear commits
  5. ASSESS — Apply the coherence checklist

Coherence Checklist

When examining a commit, assess:

Read the full file on GitHub · 115 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. 2d ago First seen · 115 lines · 51 tokens per session scan A 24e43a93cc61

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens