Borrowing it
Nothing to install: this file belongs to NinjaScoutZ/houmi-mcp. 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/NinjaScoutZ/houmi-mcp/main/.agents/skills/houmi/SKILL.mdgit clone --depth 1 https://github.com/NinjaScoutZ/houmi-mcpWrote 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/ninjascoutz/houmi-mcp/houmi)<a href="https://agentmods.dev/skills/ninjascoutz/houmi-mcp/houmi"><img src="https://agentmods.dev/badge/skills/ninjascoutz/houmi-mcp/houmi/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.
<a href="https://agentmods.dev/skills/ninjascoutz/houmi-mcp/houmi"><img src="https://agentmods.dev/badge/skills/ninjascoutz/houmi-mcp/houmi.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00031 | $0.00660 |
| Opus 5 | $0.00015 | $0.00330 |
| Sonnet 5 | $0.00006 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
houmi 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 10d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Houmi — Master Auto-Detect (/houmi)
Single entry-point. Detects what the task needs and activates the right subsystems automatically.
Auto-Detect Pipeline
- Call
houmi_route(intent="<user request>")to classify mode and subsystems. - If Canvas/Fabric.js is involved → auto-inspect event listeners & dispose cleanup.
- If Backend/Tauri IPC is mentioned → auto-record contract to
.agents/backend_requirements.md. - If architecture diagram is needed → generate Editorial SVG via
houmi_diagram(not Mermaid). - If refactor/rename → auto-check blast radius via
houmi_graft_intel.callers. - Always auto-grill on finish via
houmi_stack_grill.
Plan Quality Standard (Mandatory for /plan and /ultradeep)
When creating plans or modifying files, ALWAYS follow this standard:
For Every [MODIFY] Section:
- Current State — Read and cite the actual code (file:line). Never guess.
- What Changes — Show before→after diff or exact additions/deletions.
- Why — Explain the reason. What breaks without this change?
- Blast Radius — List every file that imports/uses the changed symbol.
Anti-Patterns (NEVER DO):
- ❌ "Ensure X is supported" without reading if X already exists
- ❌ "Add rotation support" without checking
rotation_degalready exists at L28 - ❌ One-liner [MODIFY] sections with no context
- ❌ Proposing new fields without checking
extra_metadatafor duplicates
Quality Gate:
Before presenting a plan to the user, self-check:
- Can a developer who never saw this codebase understand EXACTLY what to do from reading the plan alone?
- Does every [MODIFY] section cite actual line numbers from
view_file? - Are there machine-checkable acceptance tests for every LEDGER card?
If the answer to any of these is NO, the plan is not ready. Go deeper.
MCP Tool Reference
All tools live on ServerName="houmi-core":
| Tool | Purpose |
|---|---|
houmi_route |
Auto-detect intent → recommended mode & subsystem triggers |
houmi_ledger |
Fable5 task cards: init, pop_card, add_card, close_card (evidence required) |
houmi_backend_sync |
Record/list Tauri IPC & REST API contracts |
houmi_stack_grill |
Scan for Type any, Canvas leaks, hardcoded colors, hollow code |
houmi_graft_intel |
Symbol callers (blast radius) and file skeleton (API at a glance) |
houmi_diagram |
Editorial SVG architecture diagrams (Dark Obsidian / Minimal Light) |
houmi_guard |
Write-guard path allowlisting per phase |
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.
- 10d ago First seen · 54 lines · 31 tokens per session scan A e5b24dbf7275
houmi is a skill published in the GitHub repository NinjaScoutZ/houmi-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 31 tokens to every session and 660 once invoked, about $0.0002 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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…