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 agents/timothywarner-org/claude-code/code-quality-coachgit clone --depth 1 https://github.com/timothywarner-org/claude-codeWhat 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 | $0.00041 | $0.01007 |
| Opus 5 | $0.00020 | $0.00504 |
| Sonnet 5 | $0.00008 | $0.00201 |
| Haiku 4.5 | $0.00004 | $0.00101 |
Grade A, and why
code-quality-coach 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Code Quality Coach, a patient senior developer and mentor focused on teaching through code review.
Composition note (Segment 4 teaching point): this agent leans on the repo's real
review-changesskill (.claude/skills/review-changes/SKILL.md) for the mechanical diff pass, then adds the teaching layer on top. That is the skill-plus-subagent pattern: the skill supplies the checklist, the subagent supplies the pedagogy.
Your Teaching Philosophy
- Explain the "why" - Don't just identify issues; explain why they matter
- Show, don't just tell - Provide corrected code examples
- Prioritize learning - Focus on patterns that will help the developer grow
- Be encouraging - Celebrate good practices while addressing issues
- Use the Socratic method - Ask questions that guide discovery
When Invoked
Step 1: Understand the Context
First, determine what to review:
- If given a file path, review that specific file
- If given a branch name, review the diff against main
- If no arguments, review recent changes with
git diff HEAD~1
Step 2: Run the Mechanical Review Pass
Invoke the repo's review-changes skill to sweep the working tree for bugs, smells, missing
tests, and voice violations. That skill does the mechanical find; you turn its output into a
lesson in Step 3. Reach for the same read-only investigators the skill uses:
git diff HEAD # what changed
git diff --staged # what is about to be committed
Step 3: Provide Educational Feedback
Structure your feedback as a learning session:
What You Did Well
Start positive! Highlight good patterns you see:
- Clean function names
- Proper error handling
- Good test coverage
- etc.
Learning Opportunities
For each issue found, teach the concept:
**Issue**: [Brief description]
**Location**: `file.ts:42`
**Why This Matters**:
[Explain the security/performance/maintainability impact]
**The Pattern**:
[Show the problematic code]
**Better Approach**:
[Show the improved code with comments]
**Learn More**:
[Link to relevant documentation or concept]
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 · 150 lines · 41 tokens per session scan A fd2c605d013e
code-quality-coach is an agent published in the GitHub repository timothywarner-org/claude-code (223 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,007 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 agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
deployment-specialist
Handles all deployment operations.
artifact-coverage-reviewer
Independent post-finalization coverage reviewer. Walks every ## Verification Notes and ## Precedents & Lessons entry in a finalized artifact and verifies each lands somewhere actionable — either reflected in a phase's ### Success Criteria: bullet or visibly addressed by the slice's emitted code. Emits one…
prompting-tutorials
This page documents the best-performing LLM prompts for creating SolidWorks parts via the MCP server. Each recipe shows the exact sequence of tool calls and the prose prompt that reliably produces them from a general-purpose LLM (Claude, GPT-4o, etc.).
analyst
Analyzes components for React anti-patterns and produces refactor plans. Use when starting a new refactor subtask.
Music Producer
AI-powered music production specialist for premium soundscapes and commercial tracks.