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/lync-cyber/cataforge/claude-mdgit clone --depth 1 https://github.com/lync-cyber/CataForgeWrote 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/lync-cyber/cataforge/claude-md)<a href="https://agentmods.dev/instructions/lync-cyber/cataforge/claude-md"><img src="https://agentmods.dev/badge/instructions/lync-cyber/cataforge/claude-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 | $0.03945 | $0.03945 |
| Opus 5 | $0.01972 | $0.01972 |
| Sonnet 5 | $0.00789 | $0.00789 |
| Haiku 4.5 | $0.00394 | $0.00394 |
Grade A, and why
CataForge 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 5d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CataForge — Claude Code 项目指令
项目信息
- 技术栈: Python ≥3.11 · Click(CLI) · pyoxigraph/RDF/SHACL(知识图谱) · linkml(schema) · pytest + ruff + pre-commit
- 运行时: claude-code
- 框架版本: 0.19.0
- 语言定位: 中文框架（提示词/文档/交互用中文；代码/变量/CLI参数用英文）
- 执行模式: standard
- 阶段配置: 以下阶段可在 Bootstrap 时标记为 N/A 以跳过:
- ui_design: 后端/CLI/API-only 项目可跳过（默认行为）
- testing: 原型/PoC 项目可跳过
- deployment: 库/SDK 项目可跳过
- model 继承: AGENT.md 中
model: inherit继承父会话模型；可用model: <model-id>覆盖
执行环境 (Bootstrap 时由 cataforge setup env-block 填入)
- 技术栈: python
- 包管理器: uv
- 安装命令:
uv sync - 测试命令:
uv run pytest -n auto --dist loadscope（全量并行；快速迭代档加-m "not slow"，与 CI 同口径。裸uv run pytest串行全量含 slow e2e，仅调试单文件时使用） - Lint 命令:
uv run ruff check
项目状态 (orchestrator专属写入区，其他Agent禁止修改)
- 项目性质: CataForge 是成熟、持续迭代的 AI SDLC 框架本体（meta 项目），自身按框架工程流程演进 —— feature branch + PR + Squash merge + TDD +
run_local.py/CI 门禁；不运行 orchestrator 的 7 阶段 SDLC 文档管线 - SDLC 文档管线对本仓 N/A: PRD / ARCH / UI-SPEC / DEV-PLAN / TEST-REPORT / DEPLOY-SPEC 是框架交付给下游业务项目的产物，对元项目本身不需要（非"未开始"）
- 进度事实源: git 历史 / PR / CHANGELOG /
docs/proposals/，不在本文件维护阶段或文档状态字段 - 剩余 backlog（真实状态以各提案头部为准，本行仅防遗忘指针）:
- penpot-bridge C2 + E ——
docs/proposals/penpot-bridge-convergence.md（核心已落，C2/E 子项延期）
- penpot-bridge C2 + E ——
- Learnings Registry: (compacted; archive in .cataforge/learnings/registry-archive.md)
文档导航
- 导航索引:
docs/.doc-index.json（机器索引，所有 Agent 通过cataforge context read查询；缺失时运行cataforge context index重建） - 通用规则: .claude/rules/COMMON-RULES.md
- 子代理协议: .claude/rules/SUB-AGENT-PROTOCOLS.md
- 编排协议: .cataforge/agents/orchestrator/ORCHESTRATOR-PROTOCOLS.md (orchestrator专属)
- 状态码Schema: .cataforge/schemas/agent-result.schema.json
- 加载原则: 按章节/条目粒度按需通过
cataforge context read加载，不全量加载
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.
- 5d ago First seen · 196 lines · 3,945 tokens per session scan A 5a511b303e14
CataForge CLAUDE.md is an instructions file published in the GitHub repository lync-cyber/CataForge (128 stars, last pushed 1mo ago), licensed MIT. It adds 3,945 tokens to every session, about $0.0197 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
vscode buildNext.instructions.md
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).
spec-kit AGENTS.md
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.
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.
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).
langchain AGENTS.md
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.