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/codenamev/claude_memory/review-commitnpx skills add codenamev/claude_memory --skill review-commitgit clone --depth 1 https://github.com/codenamev/claude_memoryWhat 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 | $0.00025 | $0.01671 |
| Opus 5 | $0.00013 | $0.00835 |
| Sonnet 5 | $0.00005 | $0.00334 |
| Haiku 4.5 | $0.00003 | $0.00167 |
Grade A, and why
review-commit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Commit Quality Review
Review the staged changes in this commit for code quality issues before committing.
Objectives
- Fast: Complete review in < 30 seconds
- Focused: Only review staged Ruby files
- Actionable: Clear pass/fail with specific fixes
- Non-interactive: Works in headless mode
- Expert-driven: Apply Ruby best practices from industry experts
Expert Panel
Apply principles from these Ruby/software design experts:
- Sandi Metz - POODR principles, small methods/classes, SRP, DRY
- Jeremy Evans - Sequel best practices, transaction safety, performance
- Kent Beck - Simple design, revealing names, Command-Query Separation
- Avdi Grimm - Confident Ruby, null objects, tell-don't-ask, meaningful returns
- Gary Bernhardt - Functional core/imperative shell, fast tests, immutability
Review Process
-
Get staged files:
git diff --cached --name-only --diff-filter=ACM | grep '\.rb$' -
For each staged Ruby file, check:
- Get the full diff:
git diff --cached <file> - Review only the added/modified lines (lines starting with
+)
- Get the full diff:
-
Look for critical issues (❌ BLOCK):
Sandi Metz violations:
- ❌ Missing
frozen_string_literal: truein new files - ❌ Methods > 15 lines (SRP violation, too complex)
- ❌ Classes > 200 lines (god object)
- ❌ Obvious code duplication (DRY violation)
Jeremy Evans (Sequel) violations:
- ❌ Raw SQL strings instead of Sequel dataset methods
- ❌ Database writes without transaction wrapper
- ❌ N+1 queries (multiple queries in loops)
Kent Beck violations:
- ❌ Overly complex solutions (nested conditionals > 3 levels)
- ❌ Command-Query Separation violation (methods that both mutate and return calculated values)
Avdi Grimm violations:
- ❌ Defensive nil checks everywhere (should use null objects)
- ❌ Implicit nil returns in public methods
- ❌ Bare
raiseorrescuewithout exception class
- ❌ Missing
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 · 200 lines · 25 tokens per session scan A 8b17a53934dd
review-commit is a skill published in the GitHub repository codenamev/claude_memory (24 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 1,671 once invoked, about $0.0001 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 2026-08-30.
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…