opencode-mcp AGENTS.md

A set of repository instructions for opencode-mcp, a TypeScript server that answers read-only questions about GitHub code repositories using a local checkout.

In plain words
What is it for?
Use it while developing opencode-mcp to understand its modules and run linting, type checks, builds, and tests before submitting changes.
Why use it?
It records the project structure, required commands, conventions, and rules that must remain intact when changing the code.

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/mvagnon/opencode-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/mvagnon/opencode-mcp

Made for: Codex, OpenCode.

Per session 1,107 This file is loaded in full into every session.
When invoked 1,107 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 $0.01107 $0.01107
Opus 5 $0.00553 $0.00553
Sonnet 5 $0.00221 $0.00221
Haiku 4.5 $0.00111 $0.00111

Measured yesterday against content hash 61a3ab1cc659, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opencode-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 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.

AGENTS.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — opencode-mcp

MCP stdio server (TypeScript, ESM) exposing one tool, ask_codebase: read-only Q&A over GitHub repositories, answered by a headless opencode run inside a locally managed checkout.

Commands

npm run lint        # eslint (flat config, eslint.config.mjs)
npm run typecheck   # tsc --noEmit — run after every change
npm run build       # emit dist/ (the shipped artifact)
npm test            # node:test on src/*.test.ts (runs .ts natively, no build)

CI (.github/workflows/ci.yml) runs exactly these four on every push/PR — all must pass.

Architecture

One module per responsibility, all under src/, kebab-case filenames:

Module Responsibility
index.ts Bootstrap: create McpServer, register the tool, connect stdio transport
ask-codebase.ts Tool registration, input validation, opencode run + retry, output shaping
get-repo.ts Deterministic clone/fetch/hard-resync (ensureRepo), fetch policy (needsFetch)
manifest.ts JSON manifest of checkouts, atomic writes, mutex-guarded
proc.ts Subprocess runner: hard timeout, 15 s heartbeat, abort-signal kill
config.ts All env-driven configuration, resolved once at startup
mutex.ts Minimal FIFO async mutex
logger.ts Timestamped stderr logging

Call flow: ask_codebaseensureRepo (fetch lock → manifest → getRepo if the policy requires) → run(opencode run …) with cwd = checkout → truncated answer + notes.

Hard invariants — do not break

  • stdout is the MCP protocol channel. Never console.log; log via logger.ts (stderr) only.
  • The tool is READ-ONLY. The prompt preamble in buildPrompt forbids writes; never add write/exec capabilities to the tool surface.
  • The manifest format is a shared contract. Keys dir, branch, fetched_at (ISO 8601) under owner/repo — previous implementations wrote the same file; keep it compatible, keep writes atomic (tmp + rename).
  • Fetching is deterministic. All user-facing fetch failures go through GetRepoError and are returned verbatim; never let raw exceptions leak to the client as generic errors.
  • Long subprocesses must heartbeat. Any run that can exceed the client's timeout takes the heartbeat callback (progress every 15 s, no-op without a client progressToken).
  • Cancellation kills children. Thread extra.signal into every run() call; an aborted request must never leave a git or opencode process behind.
  • Error results use isError: true with the message as text content, so the calling LLM sees them.

Read the full file on GitHub · 65 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. yesterday First seen · 65 lines · 1,107 tokens per session scan A 61a3ab1cc659

Subscribe to this mod's changes

opencode-mcp AGENTS.md is an instructions file published in the GitHub repository mvagnon/opencode-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,107 tokens to every session, about $0.0055 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.