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 skills add HappyMonkeyAI/AgentsProtocol --skill mcp-intent-routinggit clone --depth 1 https://github.com/HappyMonkeyAI/AgentsProtocolWrote 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/happymonkeyai/agentsprotocol/mcp-intent-routing)<a href="https://agentmods.dev/skills/happymonkeyai/agentsprotocol/mcp-intent-routing"><img src="https://agentmods.dev/badge/skills/happymonkeyai/agentsprotocol/mcp-intent-routing/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/happymonkeyai/agentsprotocol/mcp-intent-routing"><img src="https://agentmods.dev/badge/skills/happymonkeyai/agentsprotocol/mcp-intent-routing.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 | $0.00038 | $0.00555 |
| Opus 5.5 | $0.00015 | $0.00222 |
| Sonnet 5.5 | $0.00008 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
mcp-intent-routing 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP intent routing
Operationalizes ADR-0003 and root MCP.md.
When to use
- Session start / Sanity grounding on a protocolized repo
- Task needs security scan, research, capacity leases, ports/projects, browser QA, DB schema, GitHub, …
- Bootstrap or refresh project MCP awareness
- Tempted to say “no MCP for that” or improvise in shell first
Procedure
- Read
MCP.md. IfMCP.local.mdexists, read it second (overrides host paths only; does not erase core intents). - Match intent to a table row.
- If tools present in session → use them.
- If missing → dynamic_proxy:
proxy_search_tools/proxy_list_available_serversproxy_activate_server(or document Hermes config gap for the human)- optional
proxy_handshakewith project context
- One live failure after search/activate → then shell/gh fallback; note gap in handoff / MCP.local.md “wanted.”
- Never print secrets from env or config into chat, memory, or MCP.md.
Bootstrap snippet (project install)
1. Ensure spine: AGENTS.md, CONTEXT.md, MCP.md (copy from protocol), README
2. Discover: proxy list/search + known swarm mounts + optional LAN notes from operator
3. Write MCP.local.md from templates/MCP.local.md.example
4. Register project in launcher_registry if missing
5. Continue LTM bootstrap (BOOTSTRAP.md) using MCP to verify claims where possible
Intent shortcuts
| Need | Try first |
|---|---|
| Heavy build/test/parallel | resource_sentinel |
| Ports / where is repo | launcher_registry |
| Security audit | AuditScan |
| Planning research | article-research-mcp → else brave/perplexity/fetch |
| Live UI proof | browseros-neo / playwright |
| Activate unknown | dynamic_proxy |
| Wiki/notes | basic-memory |
Anti-patterns
- Empty
proxy_list_active_servers⇒ “no MCPs exist” - Skipping sentinel when installed
- Putting tokens in MCP.local.md
- Treating AuditScan as full Owner acceptance (ADR-0001)
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 · 57 lines · 38 tokens per session scan A 00c38e3f69a7
mcp-intent-routing is a skill published in the GitHub repository HappyMonkeyAI/AgentsProtocol (5 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 555 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
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…
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.