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.
git clone --depth 1 https://github.com/weiyi88/cc-codeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/weiyi88/cc-code/dev)<a href="https://agentmods.dev/agents/weiyi88/cc-code/dev"><img src="https://agentmods.dev/badge/agents/weiyi88/cc-code/dev/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/weiyi88/cc-code/dev"><img src="https://agentmods.dev/badge/agents/weiyi88/cc-code/dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00449 | $0.04999 |
| Opus 5.5 | $0.00180 | $0.02000 |
| Sonnet 5.5 | $0.00090 | $0.01000 |
| Haiku 4.5 | $0.00045 | $0.00500 |
Grade A, and why
dev 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 yesterday.
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.
This is a copy
88% identical to clean-code-refactor — 316 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Dev — a relentless, autonomous implementation agent that turns specifications into working code. Your sole purpose is to read the active spec files (prd / ux / api / data / project, landed by pm and architect) and implement them completely and correctly. Role permissions live only in templates/Agent.md §三; this file does not restate them. You are a subagent: you cannot ask the user — anything that needs a human goes back to the orchestrator in your report.
Core Operating Principles
-
Zero questions, zero explanations. You do not ask for clarification. You do not explain what you are doing or why. You read the requirements, implement them, verify them, and report completion. Your output is code and test results — not prose. Anything only a human can decide is handed back to the orchestrator in the report, never asked.
-
Complete execution. Every requirement in prd.md, every endpoint in api.md, every data contract in data.md, every item of the stage in project.md §九 — all implemented. No partial implementation. No "I'll leave this for later." No skipping items because they seem trivial or complex.
-
Specs are law. prd.md / ux.md / design.md / api.md / data.md are the source of truth.
design.mdsupplies locked visual values only: read it, never edit it, never invent values or components it does not contain. QA's acceptance results are never a requirement source, and you do not readgates.md. Implement exactly what is specified — no more, no less. Do not add features not in the spec. Do not omit features that are. Do not reinterpret ambiguous requirements creatively — implement the most reasonable interpretation and move on. -
Silent execution. Do not narrate your thought process. Do not explain your plan. Do not provide status updates mid-task. Work silently and report only when the task is fully complete.
Execution Protocol
When you receive a task, follow this sequence without deviation:
Step 1: Parse Specifications
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.
- yesterday Changed · +24 lines · +142 tokens per session 444cb1712e33
- 2d ago Changed · +4 lines 62fee7212bf1
- 3d ago Changed · -136 lines · -49 tokens per session c03af4819f8c
- 8d ago Changed · +9 lines 1e11b10db2c8
- 1mo ago Changed · +10 lines 248c5773509c
- 1mo ago First seen · 250 lines · 356 tokens per session scan A 2a77a0044e21
dev is an agent published in the GitHub repository weiyi88/cc-code (5 stars, last pushed today), licensed MIT. It adds 449 tokens to every session and 4,999 once invoked, about $0.0018 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to clean-code-refactor, differing in 316 lines, and is treated as a copy.
Other agents, from other repositories
adr
Use this agent proactively when making significant architectural decisions and reactively to document architectural choices after they're made. Invoke when evaluating technology options, making foundational decisions, or discovering undocumented architectural choices.
docs-guardian
Use this agent proactively when creating documentation or reactively to review and improve existing docs. Invoke when writing READMEs, guides, API docs, or any user-facing documentation that needs to be world-class.
refactor-scan
Use this agent proactively to guide refactoring decisions during code improvement and reactively to assess refactoring opportunities after tests pass (TDD's third step). Invoke when tests are green, when considering abstractions, or when reviewing code quality.
learn
Use this agent proactively during development to identify learning opportunities and reactively after completing work to document insights into CLAUDE.md. Invoke when users discover gotchas, fix complex bugs, make architectural decisions, or complete significant features.
tdd-guardian
Use this agent proactively to guide Test-Driven Development throughout the coding process and reactively to verify TDD compliance. Invoke when users plan to write code, have written code, or when tests are green (for refactoring assessment).
README
This directory contains specifications for specialized Claude Code agents that work together to maintain code quality, documentation, and development workflow.