Borrowing it
Nothing to install: this file belongs to Moonwuk/MoonMcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Moonwuk/MoonMcp/main/.claude/skills/strix-orchestration/SKILL.mdgit clone --depth 1 https://github.com/Moonwuk/MoonMcpWrote 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/skills/moonwuk/moonmcp/strix-orchestration)<a href="https://agentmods.dev/skills/moonwuk/moonmcp/strix-orchestration"><img src="https://agentmods.dev/badge/skills/moonwuk/moonmcp/strix-orchestration.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 5.1 | $0.00120 | $0.01602 |
| Opus 5 | $0.00060 | $0.00801 |
| Sonnet 5 | $0.00024 | $0.00320 |
| Haiku 4.5 | $0.00012 | $0.00160 |
Grade A, and why
strix-orchestration 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 7d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrating MoonMCP + Strix
You drive two complementary offensive tools that are both exposed to you over MCP — you never leave your agent (opencode / hermes / Claude):
- MoonMCP — fast, cheap, scope-first recon & detection. Maps the attack surface and finds leads (headers, IDOR signals, injection reflections, takeovers, secrets, redirects, GraphQL, desync indicators). Deterministic, stdlib, rate-limited, refuses out-of-scope targets.
- Strix — an autonomous AI pentester in a Docker sandbox that proves a lead by generating a working PoC (Caido proxy + browser + exploit runtime). Powerful but heavy: it runs its own LLM loop, costs real tokens/time, and exploits — so you delegate to it deliberately, not reflexively.
Think of it as: MoonMCP finds, Strix confirms.
The pipeline (find → decide → validate → merge)
-
Recon & detect with MoonMCP (cheap first). Use the operator prompts already built in (
bug_bounty_operator,deep_recon,injection_hunt): setscope_add/ aprogram, sweep passive → light active, and collect leads withadd_finding. Confirm what you can cheaply inside MoonMCP — differentialpassive_scan,http_repeater,intruder, and blind-vulnoast_*callbacks. -
Decide what deserves Strix. Only delegate leads that are (a) in scope, (b) high-value (RCE/SSRF/IDOR/auth/injection/logic), and (c) not already confirmed or refuted cheaply. Do not send Strix "test everything" — hand it a focused, evidence-backed task.
-
Delegate to Strix as a tool. Call the Strix tool (e.g.
strix_run) with:- the exact in-scope
target, - a tight
instructionthat carries the rules of engagement and the concrete lead(s) MoonMCP found (see the instruction recipe below).
strix_rundefaults towatch=True: it opens a terminal window that streams Strix's live output (falling back to a tmux session, then atail -fhint on headless boxes) so the operator can watch the autonomous run in real time. The result'slive_consolesays how it opened;MOONMCP_TERMINALforces a specific emulator,watch=Falsedisables the window. - the exact in-scope
-
Consume & merge. Take Strix's validated findings + PoCs, record them with MoonMCP
add_finding(severity + evidence), thentriage_findingsto dedupe and rank, andreport/export_findingsfor the writeup. Strix's PoC is your "confirmed" gate; a MoonMCP lead Strix could not reproduce staysunconfirmed.
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.
- 7d ago First seen · 116 lines · 120 tokens per session scan A 5634cf349971
strix-orchestration is a skill published in the GitHub repository Moonwuk/MoonMcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 1,602 once invoked, about $0.0006 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…