agent-intel-mcp AGENTS.md

agent-intel-mcp AGENTS.md is an instructions file for Codex, OpenCode from danieloza/agent-intel-mcp. It costs 281 tokens per session, scanned A, original, MIT.

A set of instructions for working on an MCP server that discovers useful agent-engineering patterns and prepares safe, reviewable AGENTS.md changes.

In plain words
What is it for?
Use it when changing the server, its suggestions, storage, prompts, tests, or CI workflows.
Why use it?
It gives coding agents the project’s mission, technology choices, working rules, and validation commands.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/danieloza/agent-intel-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/danieloza/agent-intel-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for agent-intel-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/danieloza/agent-intel-mcp/agents-md.svg)](https://agentmods.dev/instructions/danieloza/agent-intel-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/danieloza/agent-intel-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/danieloza/agent-intel-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 281 This file is loaded in full into every session.
When invoked 281 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00281 $0.00281
Opus 5 $0.00140 $0.00140
Sonnet 5 $0.00056 $0.00056
Haiku 4.5 $0.00028 $0.00028

Measured 2d ago against content hash 618422d14372, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-intel-mcp 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 2d 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.

AGENTS.md · 41 lines

What it actually says

AGENTS.md

Mission

Build a portfolio-grade MCP server that discovers high-signal agent-engineering patterns and turns them into safe, reviewable AGENTS.md updates.

Stack

  • TypeScript on Node.js 24
  • MCP stdio server via @modelcontextprotocol/sdk
  • OpenAI Responses API for suggestion synthesis
  • GitHub API via Octokit
  • SQLite via better-sqlite3

Working Rules

  • Keep the server non-destructive. Patch previews are preferred over direct writes.
  • Preserve deterministic fallbacks when external APIs are unavailable.
  • Favor small, composable modules in src/core/*.
  • Store durable scan and suggestion state in .agent-intel/agent-intel.db.
  • Keep clustering deterministic enough to test when embeddings are unavailable.
  • When changing prompts or suggestion logic, keep the JSON output contract stable.

Validation

  • Run npm run build
  • Run npm test
  • Run npm run lint

MCP Surface

  • Tools live in src/mcp/server.ts
  • Business logic lives in src/core/
  • Persistence lives in src/storage/
  • CI and release workflows live in .github/workflows/

Change Expectations

  • Add tests for new extraction or suggestion heuristics.
  • Document major architectural changes in docs/ARCHITECTURE.md.
Changes

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.

  1. 2d ago First seen · 41 lines · 281 tokens per session scan A 618422d14372

Subscribe to this mod's changes

agent-intel-mcp AGENTS.md is an instructions file published in the GitHub repository danieloza/agent-intel-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 281 tokens to every session, about $0.0014 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.