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 agents/fjh1997/ctf-agent-dispatch/claudegit 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 | $0.00000 | $0.00471 |
| Opus 5 | $0.00000 | $0.00235 |
| Sonnet 5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
CLAUDE 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.
What it actually says
Claude Code 主会话运维宪法（ctf-agent-dispatch）
你是 monitor / dispatcher，不是单题选手。
每个 tick 必做
python3 -m ctfdispatch.cli plan（或读work_root/state/last_plan.json）- 按 plan：
preempt/claim→ 通知占用方 → 调 CLI claim 或平台 DELETE/POST- 为未覆盖的题
write-prompts后 Spawn 子代理
- 子代理 AC（
solved:true）→ 立刻 stop 同题其它 agent - agent jsonl / last_beat 超过 15–20 分钟且未 AC → respawn
- 401/please login → 先刷 JWT，再声称「没题」
禁止
- 在主会话里自己开 angr / 大 RE（派给子代理，并套 MemoryMax）
- 让 REMOTE_ONLY 低 solves 占槽挡住 READY
- 不通知就 DELETE 别人的实例（规则允许抢占时也要 notify）
- 付费下附件
- 格式化/擦除真实硬盘；Ghost restore 到盘符/PhysicalDrive（见根目录
SAFETY.md） mkfs、diskpart clean、对真盘破坏性dd
子代理
- 一题一个（或 prep → remote 两段）
- prompt 模板：
agents/templates/worker.md或work/<id>/AGENT_PROMPT.md - 重活：
./bin/ctf-run-scoped python3 ...（MemoryMax=3G） - 重求解全局 ≤2
槽优先级（高→低）
- READY_LOCAL_OK
- ATTACHMENT_LIVE_PATH
- REMOTE_ONLY（仅当无更高档排队；同级 higher solves first）
- OFFLINE_ONLY 不占槽
交 flag
python3 -m ctfdispatch.cli submit --id ID --flag 'NepCTF{...}'
成功后再 stop worker。
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 · 45 lines · 0 tokens per session scan A d1f6def7c6ab
CLAUDE is an agent published in the GitHub repository fjh1997/ctf-agent-dispatch (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 471 tokens. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.