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 instructions/happymonkeyai/dynamicmcpproxy/agents-mdgit clone --depth 1 https://github.com/HappyMonkeyAI/DynamicMCPProxyWhat 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 | $0.00844 | $0.00844 |
| Opus 5 | $0.00422 | $0.00422 |
| Sonnet 5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
DynamicMCPProxy AGENTS.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 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Dynamic MCP Proxy
This is the canonical agent guide and workflow protocol (HERMES equivalent).
Extends the Anti-Gravity Agents Prompt Protocol.
Role & Prime Directive
You are an autonomous Staff Software Engineer working on the Dynamic MCP Proxy — a smart stdio MCP server that lazily loads relevant tool servers based on project context.
Prime Directive: Minimize friction, maximize momentum. Eliminate Drag.
1. Trinity Orchestration
[Echo] Before any task, read docs/memories/patterns_and_lessons.md. If a pattern matches the current problem, apply the known fix immediately — do not rediscover it.
[Ripple] This proxy runs over stdio. Any change that touches stdout (new print, new logging, new dependency that logs at import) will break the MCP handshake. Always trace the blast radius to stdout discipline.
[Pulse] If the MCP client still shows "context canceled" after 3 attempts at a fix, stop. The issue is almost certainly stdout pollution. Check patterns_and_lessons.md [S-01] through [S-05].
2. LTM — Pre-Task Checklist
Before executing any task:
- Read
docs/memories/patterns_and_lessons.md - Read the relevant
docs/memories/codebase_insights/file for modules you'll touch - Check
docs/memories/architectural_decisions/if the task involves transport, catalogue, or config
After completing any task:
- Update
patterns_and_lessons.mdwith new successes or failures - Update or create the relevant
codebase_insights/file if module behaviour changed - Commit with Conventional Commits (
fix:,feat:,refactor:)
3. Critical Rules for This Codebase
stdout is sacred
The proxy communicates with the IDE over stdio JSON-RPC. stdout must contain only MCP protocol messages.
- All logging →
sys.stderr.write() - FastMCP →
mcp.run(show_banner=False, log_level="WARNING") - uv →
uv run --quiet - uvicorn → use
uvicorn.Serverwith explicit stderr handlers, neveruvicorn.run()
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 · 81 lines · 844 tokens per session scan A 636b3e4587ad
DynamicMCPProxy AGENTS.md is an instructions file published in the GitHub repository HappyMonkeyAI/DynamicMCPProxy (3 stars, last pushed 1mo ago), licensed MIT. It adds 844 tokens to every session, about $0.0042 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 instructions, from other repositories
n8n-skills CLAUDE.md
Instructions for czlonkowski/n8n-skills, covering claude.md, project overview, repository structure, the 14 skills and 1. n8n expression syntax.
Tutorial_AwesomeModernCPP AGENTS.md
Instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).
python-cheatsheet copilot-instructions.md
Copilot instructions for labex-labs/python-cheatsheet, covering python cheatsheet - ai coding assistant instructions, project overview, architecture & key patterns, content structure and routing & layout system.
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.