context-repo-mcp: Instructions file for Codex

AGENTS.md

context-repo-mcp AGENTS.md is an instructions file for Codex, OpenCode from Gitmaxd/context-repo-mcp. It costs 619 tokens per session, scanned A, original, MIT.

Repository instructions for a small Node.js bridge that forwards MCP requests to the hosted Context Repo service.

In plain words
What is it for?
Use them when developing, testing, or reviewing the context-repo-mcp bridge and its JSON-RPC communication.
Why use it?
They document the bridge’s architecture, configuration, testing rules, and transport requirements so changes do not duplicate or alter the hosted service’s behavior.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is Gitmaxd/context-repo-mcp's own configuration. It tells Codex and OpenCode how to work on context-repo-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything context-repo-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Gitmaxd/context-repo-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.

Copy the file
curl -O https://raw.githubusercontent.com/Gitmaxd/context-repo-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Gitmaxd/context-repo-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 context-repo-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gitmaxd/context-repo-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/gitmaxd/context-repo-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/gitmaxd/context-repo-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/gitmaxd/context-repo-mcp/agents-md/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.

agentmods 80×15 button for context-repo-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gitmaxd/context-repo-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/gitmaxd/context-repo-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 619 This file is loaded in full into every session.
When invoked 619 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00619 $0.00619
Opus 5.5 $0.00248 $0.00248
Sonnet 5.5 $0.00124 $0.00124
Haiku 4.5 $0.00062 $0.00062

Measured 1mo ago against content hash 5b9b9055b433, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

context-repo-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 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.

AGENTS.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<coding_guidelines>

context-repo-mcp

This package is the official network-dependent stdio bridge to the hosted Context Repo MCP at https://contextrepo.com/mcp.

Architecture

stdio MCP client
  -> src/index.js
  -> src/bridge.js
  -> https://contextrepo.com/mcp
  • src/config.js resolves and validates environment configuration.
  • src/index.js frames newline-delimited stdin, dispatches concurrently, and writes JSON-RPC responses to stdout.
  • src/bridge.js performs one opaque HTTP POST and classifies the response.

The hosted MCP is the only owner of tools, prompts, resources, schemas, business errors, and output shapes. Do not add local registrations, REST dispatch, formatters, or Context Repo business behavior.

Build and test

npm install
npm test
npm ls --all
npm pack --dry-run
  • Package manager: npm
  • Runtime: Node.js 18 or later
  • Modules: ES modules
  • Tests: built-in node:test
  • Dependencies: none

Tests must use injected fetch or loopback servers bound to 127.0.0.1. Automated tests must not call contextrepo.com or require a real API key.

Transport invariants

  • Send the exact input line as the HTTP body.
  • Relay valid hosted JSON-RPC text without parsing and reserializing it.
  • Preserve content, structuredContent, _meta, and unknown fields.
  • Append only the terminating LF on stdout.
  • Keep stdout JSON-only; diagnostics belong on stderr.
  • Never log keys, authorization headers, request bodies, response bodies, stack traces, filesystem paths, or raw network errors.
  • Do not retry POST requests.
  • Use redirect: "error", a 90-second abort timeout for reason, and a 30-second abort timeout for other requests.
  • Treat SSE, multiline JSON, malformed JSON, and non-JSON responses as failures. Do not add an SSE parser.

Configuration

  • CONTEXTREPO_API_KEY: canonical API key.
  • CONTEXT_REPO_API_KEY: deprecated compatibility alias.
  • CONTEXTREPO_MCP_URL: development/test MCP endpoint override.
  • Default endpoint: https://contextrepo.com/mcp.

Read the full file on GitHub · 79 lines

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. 1mo ago Changed · +1 lines · +16 tokens per session 5b9b9055b433
  2. 2mo ago First seen · 78 lines · 603 tokens per session scan A 8986d163dde6

Subscribe to this mod's changes

context-repo-mcp AGENTS.md is an instructions file published in the GitHub repository Gitmaxd/context-repo-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 619 tokens to every session, about $0.0025 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 2026-08-31.

Related

context-repo-mcp AGENTS.md compared with instructions from other repositories

context-repo-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
context-repo-mcp AGENTS.mdGitmaxd/context-repo-mcpInstructions file11mo agoMITA619Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot