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/the-code-registry/mcp-server/agents-mdgit clone --depth 1 https://github.com/The-Code-Registry/mcp-serverWhat 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 | $0.01531 | $0.01531 |
| Opus 5 | $0.00766 | $0.00766 |
| Sonnet 5 | $0.00306 | $0.00306 |
| Haiku 4.5 | $0.00153 | $0.00153 |
Grade A, and why
mcp-server 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This project exposes an MCP server for creating and analyzing code vaults via The Code Registry - the World's first code intelligence and insight platform built for business leaders.
MCP endpoints
- Web app:
https://app.thecoderegistry.com - MCP server:
https://integrator.app.thecoderegistry.com(POST to/api/ai/router)
Discovery
Use tools/list to discover available MCP tools and their input schemas.
Use resources/list and resources/read for documentation, workflows, and examples.
Use prompts/list and prompts/get for curated prompt templates.
Client compatibility note (Cursor / CallMcpTool wrappers)
- Known issue in some clients (notably some Cursor builds): the displayed
CallMcpToolschema may omitargumentseven though runtime forwarding supports it. - For The Code Registry tools, always pass required tool inputs via
CallMcpTool.arguments. - If a tool has no required inputs, use
arguments: {}for consistency. - Example wrapper call shape:
{
"server": "coderegistry",
"toolName": "create-code-vault",
"arguments": {
"project_id": "<project_id>",
"user_id": "<user_id>",
"name": "My Code Vault",
"source_type": "LOCAL_AGENT"
}
}
Authentication
create_accountdoes not require an API key.- All other MCP actions require
X-API-Keyusing the key returned bycreate_account. - Existing users can generate an API key in the web app and provide it directly via
X-API-Key. - If an MCP client cannot set custom headers, include
api_keyin the toolarguments. Header auth is preferred when available.
Plan behavior
- Free tier is limited to 100,000 total lines of code across all vaults.
- Free tier should still support registration, project/vault lifecycle, code sync, and summary-level analysis retrieval.
- Paid plans unlock extended functionality and richer payloads (for example full findings, verification badges/public verification pages, and Code Score out of 1,000).
- If a feature is plan-restricted, return the service error and direct users to upgrade in the web app.
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 · 190 lines · 1,531 tokens per session scan A 74c9651735d3
mcp-server AGENTS.md is an instructions file published in the GitHub repository The-Code-Registry/mcp-server (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,531 tokens to every session, about $0.0077 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
roam-code AGENTS.md
Instructions for Cranot/roam-code, covering agents.md — roam-code development guide, what this project is, documentation hub, where files go (private vs public) and quality discipline (from internal/dogfood/ + agi-in-md).
truecourse CLAUDE.md
Instructions for truecourse-ai/truecourse, covering truecourse — claude instructions, key files to keep updated, project layout, development commands and storage.
truecourse AGENTS.md
Instructions for truecourse-ai/truecourse, covering truecourse — codex instructions, key files to keep updated, project layout, development commands and rules.
codeseek CLAUDE.md
Instructions for CodeBendKit/codeseek, covering claude.md, build & test, enter rust project directory, build and run tests.
bonsai-ninja AGENTS.md
Instructions for gromhacks/bonsai-ninja, covering bonsai-ninja, map a codebase, optional explicit semantic sidecar prewarm, explicit spelling for default syntax/construct indexing and optional during active editing.
ScalaSemantic AGENTS.md
Instructions for MercurieVV/ScalaSemantic, covering agents.md instructions and quick start.