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 instructions/wzj998/chatccc/agents-mdgit clone --depth 1 https://github.com/wzj998/ChatCCCWrote 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/instructions/wzj998/chatccc/agents-md)<a href="https://agentmods.dev/instructions/wzj998/chatccc/agents-md"><img src="https://agentmods.dev/badge/instructions/wzj998/chatccc/agents-md.svg" alt="Measured on agentmods" 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 | $0.00831 | $0.00831 |
| Opus 5 | $0.00415 | $0.00415 |
| Sonnet 5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
ChatCCC AGENTS.md 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ChatCCC CLAUDE.md — 100% identical, 0 lines differ
What it actually says
协作原则(核心)
- 第一性原理思考:从原始需求和问题出发。若动机或目标不清晰,先讨论;若路径不是最优,直接指出并建议更好的做法
- 重要改动先补测试护栏:若改动范围大且影响重要,且相关路径没有或不足单元测试覆盖,须先完善对改动前行为的单测,再改实现
开发注意点
cmt/cmt all约定:cmt→ 1) 修改注释和文档 2) 运行全部单测 3)git commit只提交当前会话改动。cmt all→ 上述流程但提交全部改动(含与当前对话无关的)。若无法可靠区分当前会话改动,先问用户cmp/cmp all约定:cmp→ 执行cmt后git push。cmp all→ 执行cmt all后git push- 避免
undefined被当成false使用:当函数成功时返回undefined(如.catch(() => {})没有返回值、void 函数等),直接用if (result)会把成功当成失败。必须用显式比较,例如result !== false而非!result - 公有仓库 PR 规则:ChatCCC 仓库 dev → main 的 PR 必须使用 merge commit(Create a merge commit),禁止 squash。PR 合并通过
gh pr merge时指定--merge - 六步 PR/发布法:1)
FeishuClauderPrivate/dev开发、测试、提交并推送;2) 私有仓dev → main创建并合并 PR;3) 用sync.mjs同步到公开ChatCCC/dev;4) 公开仓dev → main创建 PR 并以 merge commit 合并;5) 用sync-deepccc.mjs将公开 ChatCCC 的deepccc-agent/同步到独立deepccc-agent/main;6) 在独立仓测试、提交、推送并按需发布 npm。DeepCCC co-author 的全局配置归独立/内嵌内核,ChatCCC 只持有三态 override,私有仓负责两者的源开发与同步。 package.json编码红线:文件开头禁止 BOM(部分工具如 tsx 的readPackageJson会解析失败导致闪退)。编辑后必须用node -e "JSON.parse(require('fs').readFileSync('package.json','utf8'))"验证无 BOM 且 JSON 合法。写入时用utf8编码(不含 BOM),engines.node直接用">=20"不要用>转义
日志位置
- 运行日志、启动黑匣子和 PID/状态等用户数据默认写入用户目录:
~/.chatccc/ - Windows 常见路径:
C:\Users\<用户名>\.chatccc\logs\ - 关键文件:
~/.chatccc/logs/index-*.log:主进程运行日志~/.chatccc/logs/startup-trace.log:启动、单实例清理、信号、未捕获异常等同步落盘诊断
- 仓库根目录下的
logs/可能是旧版本或历史运行残留;排查当前 npm/dev 运行问题时,优先看~/.chatccc/logs/
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.
- 4d ago First seen · 23 lines · 831 tokens per session scan A 7fbe1cefad62
ChatCCC AGENTS.md is an instructions file published in the GitHub repository wzj998/ChatCCC (22 stars, last pushed yesterday), licensed Apache-2.0. It adds 831 tokens to every session, about $0.0042 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 instructions, from other repositories
inspecto CLAUDE.md
Instructions for inspecto-dev/inspecto, covering inspecto — claude code development guide, project overview, monorepo structure, development phases (load each file as needed) and key architectural decisions.
vibe-roast copilot-instructions.md
Copilot instructions for PinkR1ver/vibe-roast: Prioritize actionable correctness, privacy, security, behavioral regressions, and missing tests. Do not block on style-only preferences.
Ocul-PM CLAUDE.md
Claude Code instructions for bunhine0452/Ocul-PM, covering claude.md, what this is, commands, single frontend test and rust (run from src-tauri/).
Ocul-PM AGENTS.md
AGENTS.md instructions for bunhine0452/Ocul-PM, covering ocul-pm 작업 기록 규칙, 0. 시작하기 전 — 과거를 먼저 찾는다, 1. 언제 기록하는가 (5 trigger), 2. 일지 파일 규격 (도구가 없을 때만) and 3. 금지.
mcp-me copilot-instructions.md
Instructions for paladini/mcp-me, covering copilot instructions, available mcp resources, when to proactively load my profile and the askaboutme tool.
kumo-coding-agent AGENTS.md
Instructions for kumo-ai/kumo-coding-agent: All instructions, routing tables, and rules are in CLAUDE.md. Read that file as the entry point for this agent.