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/dengteng/chatcode/claude-mdgit clone --depth 1 https://github.com/dengteng/ChatCodeWhat 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 | $0.01112 | $0.01112 |
| Opus 5 | $0.00556 | $0.00556 |
| Sonnet 5 | $0.00222 | $0.00222 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
ChatCode CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
chat-code
打包规矩(重要)
- 每次完成改代码的任务后都自动打包,不用等用户开口。
- 改完代码只打包,不要自动 quit app /
pkill/ 覆盖/Applications。 原因:会搞坏用户其他会话里正在执行的任务。 - 必须签名打包,禁止打 adhoc 包。打包命令固定这一条:
(export APPLE_SIGNING_IDENTITY="$(security find-identity -v -p codesigning | awk -F'"' '/Apple Development/{print $2; exit}')" [ -n "$APPLE_SIGNING_IDENTITY" ] || { echo "无可用签名证书,停手"; exit 1; } PATH="$HOME/.cargo/bin:$PATH" npx tauri buildcargo在~/.cargo/bin,不在默认 PATH;身份从 keychain 现取,真名不落仓库) - 为什么非签不可:adhoc 包在 TCC 里靠 cdhash 认身份,每次重打包 cdhash 变,
屏幕录制/麦克风授权全部失效并重新弹窗(「隐私与安全性」里那行是残留旧记录)。
用开发者证书后 csreq 认
com.chatcode.app+ 证书,重打包授权不掉。 - 打完
codesign -dvvv <app>自检:必须是Identifier=com.chatcode.app+Authority=Apple Development: …,出现Signature=adhoc就是没签上,重来。 - 打完只告诉用户新包路径,用户自己装:
src-tauri/target/release/bundle/macos/ChatCode.app - 签名身份不写进
tauri.conf.json/package.json(会把开发者真名 + 证书 ID 提交进仓库)。
产品介绍图出完就上传(重要)
- 用
product-intro-picskill 出完一期图后自动上传,不用等用户开口:node scripts/publish-pics.mjs # 传全部期(未改动的自动跳过) node scripts/publish-pics.mjs 13-功能特性横版 # 只传这一期 node scripts/publish-pics.mjs drop chatcode/12- # 标删一批(前缀匹配) - 传到 tt-knowledge 的
[email protected]空间,vault 路径chatcode/<期目录>/<文件>。 前缀只留一层chatcode/:客户端文件列表是单行截断的,前缀长了每行都是相同的那截, 看不出是哪一期哪张图(一开始写成packages/chatcode/product-intro/,列表里全糊成一样)。 - 客户端没有通用文件夹折叠 ——
knowledge.tsx里只硬编码了images/前缀折叠成 「文章采集的图片」,其余一律平铺。要真正的分组得改 tt-knowledge 那个项目。 - 和 fortune-signal-app 的
publish-apk.mjs同一套:scripts/vault.mjs是从那边原样搬来的, 凭据共用~/.chatcode-publish.json(已登录,别重登 —— refresh token 是轮换式的, 重登会把另一端顶下线)。 - 增量靠
out/.published.json记mtime:size,跟着产物走、在.gitignore里。 图改了重跑即可,不会全量重传。
架构速记
- 前端 Tauri webview(
src/)连ws://127.0.0.1:PORT(开发 8975 / 打包 8976)。 - 后端 sidecar(
sidecar/server.mjs):每会话一个 SDKquery,走@anthropic-ai/claude-agent-sdk。 打包版被 esbuild 打进src-tauri/resources/sidecar.mjs(注释会被剥掉,别 grep 注释验证 bundle)。 - 用量条数据源:sidecar 的
usageProbe(无 prompt 常驻 query)读 SDK/api/oauth/usage, 取five_hour/seven_day的utilization。空闲会话的 GET 会回退到旧响应头快照(偏低),只认探针。 - 原生能力(文件选择器等)走
src-tauri/src/main.rs的#[tauri::command]。 阻塞型对话框(blocking_pick_folder)必须放async+spawn_blocking,否则主线程自死锁卡死。
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 First seen · 49 lines · 1,112 tokens per session scan A 4b286c95cb34
ChatCode CLAUDE.md is an instructions file published in the GitHub repository dengteng/ChatCode (5 stars, last pushed 2d ago), licensed MIT. It adds 1,112 tokens to every session, about $0.0056 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 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.