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/mathiasli152/opencode-ast-mcp/agents-mdgit clone --depth 1 https://github.com/maThiaslI152/opencode-ast-mcpWhat 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 | $0.02846 | $0.02846 |
| Opus 5 | $0.01423 | $0.01423 |
| Sonnet 5 | $0.00569 | $0.00569 |
| Haiku 4.5 | $0.00285 | $0.00285 |
Grade A, and why
opencode-ast-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.
How it starts
The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Guidance for AI Coding Agents
You are an AI agent working in this repo. Read this file in full before making changes. It documents the conventions, the MCP tools available to you, and the failure modes specific to this project.
Project at a glance
This is a Python MCP server that turns the OpenCode IDE into an agentic coding system. It exposes 9 tools backed by:
- tree-sitter for AST extraction (Python / JS / TS)
- LM Studio + Qwen 18B for local code analysis and log compression
- OpenAI-compatible LLM brain (default: OpenRouter + Claude Haiku) for cloud SDD planning and patch generation
- Podman for sandboxed test execution
You are likely operating through the MCP tools (from OpenCode) or on the MCP server code (as a contributor). These two modes have different guidance — see below.
If you are an OpenCode agent USING these tools
How the tools map onto OpenCode's plan/build mode
OpenCode itself has a plan mode (read-only) and a build mode (full write access). Of the 13 tools exposed by this server, only two are side-effecting and must wait for build mode:
- ✅ Allowed in plan mode:
get_file_skeleton,get_node,get_ast_json,list_files,get_project_overview,search_symbol,find_references,analyze_node,compress_log,get_loop_status,generate_sdd - ❌ Blocked in plan mode (use only in build mode):
execute_in_sandbox,execute_autonomous_loop_tool
generate_sdd is the bridge between the two modes: it runs entirely in
plan mode (no file writes), produces the SDD artifacts, and the user
flips to build mode for the autonomous loop to walk through plan.md.
The 4 codebase-awareness tools (list_files, get_project_overview,
search_symbol, find_references) are also read-only and may be used
freely in plan mode to scope the investigation before any code is
written. See README.md → "How it works with OpenCode plan/build mode"
for the full table.
Tool-selection rules (in priority order)
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 · 260 lines · 2,846 tokens per session scan A 53b1273ac243
opencode-ast-mcp AGENTS.md is an instructions file published in the GitHub repository maThiaslI152/opencode-ast-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,846 tokens to every session, about $0.0142 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.