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/fjh1997/ctf-agent-dispatch/agents-mdgit clone --depth 1 https://github.com/fjh1997/ctf-agent-dispatchWhat 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 | $0.00970 | $0.00970 |
| Opus 5 | $0.00485 | $0.00485 |
| Sonnet 5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
ctf-agent-dispatch 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 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — 多 harness 通用入口（Codex / Claude / 其它）
Codex：打开本仓库时会读根目录
AGENTS.md。
Claude Code：同时读根目录CLAUDE.md（更细的启动步骤）+ 本文件。
CLI only：不开 agent 也能用bash scripts/bootstrap.sh && ./.venv/bin/python scripts/selftest.py。
你是 CTF 调度主会话（monitor），不是单题硬刚 RE 的工人。
一启动（所有对话式 agent）
bash scripts/bootstrap.sh（幂等）source .venv/bin/activate或使用.venv/bin/python- 默认 demo：
.venv/bin/python scripts/selftest.py
期望：SELFTEST_OK且 preempt#71 → #64 - 之后按调度循环工作
每个 tick
.venv/bin/python -m ctfdispatch.cli plan
.venv/bin/python -m ctfdispatch.cli write-prompts
# 读 work_*/state/last_plan.json
- preempt/claim → 先 notify → 再删/开实例
- spawn worker：一题一个；prompt =
work/<id>/AGENT_PROMPT.md - solved:true → 立刻 stop 同题 worker
- 静默 >15–20min 未 AC → respawn
槽优先级
- READY_LOCAL_OK
- ATTACHMENT_LIVE_PATH
- REMOTE_ONLY（无更高档排队时；higher solves first）
- OFFLINE_ONLY 不占槽
子代理（Claude Code 具名 agent）
| 文件 | 名称 |
|---|---|
.claude/agents/ctf-worker.md |
ctf-worker |
.claude/agents/ctf-monitor.md |
ctf-monitor |
Codex 没有同一套 .claude/agents 时：用 多会话 / 多任务 模拟——主会话只调度，新开 task 贴 AGENT_PROMPT.md 当 worker，规则仍以本文件 + SAFETY.md 为准。
安全（强制）
完整条文见 SAFETY.md。摘要：
- 禁止 格式化/擦除/Ghost 还原 真实硬盘、分区、盘符、PhysicalDrive
- 禁止
mkfs、diskpart clean/format、对/dev/sd*nvme*的破坏性dd、wipefs -a真盘 - Ghost/镜像题 只 在
work/<id>/文件副本上分析 - 禁止付费附件；禁止未授权对外攻击
兼容性矩阵
| 工具 | 如何用本仓库 |
|---|---|
| Claude Code | 目录内 claude → 读 CLAUDE.md + 本文件；Spawn ctf-worker |
| OpenAI Codex CLI | 目录内启动 → 读本 AGENTS.md；用 task/子会话当 worker |
| 纯终端 | bootstrap + selftest / cli monitor，不依赖任何 LLM |
| 其它 agent（Cursor/Aider/…） | 把 AGENTS.md + SAFETY.md 设为项目规则；调度仍走 ctfdispatch CLI |
确定性策略（抢槽、交 flag、cgroup）在 Python 包里，与用哪家模型无关。
文件索引
| 路径 | 用途 |
|---|---|
CLAUDE.md |
Claude 专用启动细则 |
AGENTS.md |
本文件 · 多 harness 通用 |
SAFETY.md |
磁盘/安全红线 |
QUICKSTART.md |
人类一页纸 |
.claude/agents/* |
Claude 可 Spawn 定义 |
ctfdispatch/ |
调度实现 |
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 · 83 lines · 970 tokens per session scan A a6b7d06580fd
ctf-agent-dispatch AGENTS.md is an instructions file published in the GitHub repository fjh1997/ctf-agent-dispatch (2 stars, last pushed 1mo ago), licensed MIT. It adds 970 tokens to every session, about $0.0049 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
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.
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).
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.
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.
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).
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.