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/quality-updatenpx skills add codenamev/claude_memory --skill quality-updategit 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 | $0.00031 | $0.01664 |
| Opus 5 | $0.00015 | $0.00832 |
| Sonnet 5 | $0.00006 | $0.00333 |
| Haiku 4.5 | $0.00003 | $0.00166 |
Grade A, and why
quality-update 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quality Update - Incremental Implementation
Systematically implement code quality improvements from the review document, making tested, atomic commits for each fix.
Process Overview
- Read the quality review from
docs/quality_review.md - Prioritize improvements (start with Quick Wins, then High Priority)
- Implement fixes incrementally (one logical change at a time)
- Run tests after each change to ensure nothing breaks
- Make atomic commits that capture the change and its purpose
- Update review document to track progress
Detailed Steps
Step 1: Read and Parse Review
# Read the current quality review
Read docs/quality_review.md
Focus on these sections in priority order:
- Appendix B: Quick Wins - Start here (fast, low risk)
- High Priority (This Week) - Critical improvements
- Medium Priority (Next Week) - Important but not urgent
- Skip Low Priority items for now
Step 2: Select Next Improvement
Choose improvements based on:
- Risk: Low risk first (refactoring, style fixes)
- Dependencies: Prerequisites before dependent work
- Atomicity: Each commit should be one logical change
- Test coverage: Ensure tests exist or add them
Step 3: Implement the Fix
For each improvement:
- Read affected files to understand current state
- Make the change using Edit or Write
- Run linter to ensure style compliance:
bundle exec rake standard:fix - Run tests to verify correctness:
bundle exec rspec - Fix any test failures before proceeding
Step 4: Make Atomic Commit
Commit Message Format:
[Quality] Brief description of what was fixed
- Specific change made (e.g., "Extract DatabaseCheck from DoctorCommand")
- Why this improves quality (e.g., "Improves SRP and testability")
- Expert principle applied (e.g., "Sandi Metz: Single Responsibility")
Addresses: docs/quality_review.md [section reference]
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 230 lines · 31 tokens per session scan A 7b32af4fc03b
quality-update is a skill published in the GitHub repository codenamev/claude_memory (24 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,664 once invoked, about $0.0002 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…