What is ctf-agent-dispatch CLAUDE.md?

A set of operating instructions for an automated Capture the Flag security-solving dispatcher. It explains how the main session monitors work and starts separate worker sessions to solve tasks.

Use it to bootstrap and test the dispatcher, monitor available challenge slots, start or stop workers, check status, and connect to a real competition platform.

It turns short user commands into a repeatable workflow and includes safety rules for handling disk images without damaging real disks.

How fjh1997/ctf-agent-dispatch configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to fjh1997/ctf-agent-dispatch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/fjh1997/ctf-agent-dispatch/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/fjh1997/ctf-agent-dispatch

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/fjh1997/ctf-agent-dispatch/claude-md/github.svg)](https://agentmods.dev/instructions/fjh1997/ctf-agent-dispatch/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/fjh1997/ctf-agent-dispatch/claude-md"><img src="https://agentmods.dev/badge/instructions/fjh1997/ctf-agent-dispatch/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/fjh1997/ctf-agent-dispatch/claude-md"><img src="https://agentmods.dev/badge/instructions/fjh1997/ctf-agent-dispatch/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 532 This file is loaded in full into every session.

When invoked 532 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00532	$0.00532
Opus 5.5	$0.00213	$0.00213
Sonnet 5.5	$0.00106	$0.00106
Haiku 4.5	$0.00053	$0.00053

Measured 1mo ago against content hash 2b3a8f961450, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ctf-agent-dispatch 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 1mo 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.

CLAUDE.md · 66 lines

What it actually says

ctf-agent-dispatch

解压本目录后执行 claude 即可。你是 调度主会话。
多 harness 通用规则见 AGENTS.md；磁盘安全见 SAFETY.md（强制）。

会话一启动就做（无需用户再说明）

1. Bootstrap

bash scripts/bootstrap.sh
source .venv/bin/activate

2. Demo（默认）

除非 config.yaml 已指向真实平台且 TOKEN 有效：

.venv/bin/python scripts/selftest.py

中文汇报：SELFTEST_OK、抢槽 #71→#64、solved 列表。

3. 身份

主会话 = monitor；做题 Spawn ctf-worker
遵守 SAFETY.md：禁止格式化/Ghost 还原真实硬盘
重活 ./bin/ctf-run-scoped；单槽 READY 优先；交 flag 后 stop

用户一句话

用户	动作
空白/开始	bootstrap + selftest
tick	`cli monitor --once` + spawn/stop
status	`cli status` + last_plan
接真平台	nepctf2026.yaml + TOKEN
spawn N	worker + `work/N/AGENT_PROMPT.md`

斜杠：/demo /tick /status /bootstrap

每个 tick

.venv/bin/python -m ctfdispatch.cli plan
.venv/bin/python -m ctfdispatch.cli write-prompts

slot preempt/claim → notify → DELETE/POST
SPAWN 未覆盖题 → ctf-worker
STOP 已 solved
RESPAWN 静默超时

安全（必须每次会话重申给 worker）

详见 SAFETY.md：

禁止 mkfs / format / diskpart clean / 对物理盘 dd / Ghost restore 到真盘或盘符
镜像题只在 work/<id>/ 文件上分析
禁止付费附件

验收

selftest → SELFTEST_OK · preempt REMOTE_ONLY#71 → READY#64

Changes

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.

1mo ago First seen · 66 lines · 532 tokens per session scan A 2b3a8f961450

Subscribe to this mod's changes

ctf-agent-dispatch CLAUDE.md is an instructions file published in the GitHub repository fjh1997/ctf-agent-dispatch (2 stars, last pushed 3mo ago), licensed MIT. It adds 532 tokens to every session, about $0.0021 per session on Opus 5.5. 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.

Security

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).

microsoft/vscode · 9,715 tokens

ctf-agent-dispatch: Instructions file for Claude Code