ast-mcp AGENTS.md

ast-mcp AGENTS.md is an instructions file for Codex, OpenCode from mwillbanks/ast-mcp. It costs 1,842 tokens per session, scanned A, original, MIT.

Repository instructions for working with ast-mcp, a tool that reads and changes code through its structure rather than ordinary file editors. They define which tools and paths are allowed.

In plain words
What is it for?
They help an agent explore source code, dependencies, callers, and exact file contents, then safely update existing files or create new ones.
Why use it?
They prevent direct file changes and guide the agent toward approved ways to inspect, search, hash, and patch repository files.

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/mwillbanks/ast-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/mwillbanks/ast-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 ast-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mwillbanks/ast-mcp/agents-md.svg)](https://agentmods.dev/instructions/mwillbanks/ast-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mwillbanks/ast-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mwillbanks/ast-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,842 This file is loaded in full into every session.
When invoked 1,842 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 5.1 $0.01842 $0.01842
Opus 5 $0.00921 $0.00921
Sonnet 5 $0.00368 $0.00368
Haiku 4.5 $0.00184 $0.00184

Measured 5d ago against content hash 8bb724deb644, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 5d 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 · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AST MCP isolated environment

CRITICAL INSTRUCTION: You are operating in an AST-isolated environment.

  • Load and follow the $ast-mcp skill before exploring or changing repository files.
  • You have zero permission to create, overwrite, patch, move, or delete files through direct editor tools, apply_patch, unified patches, shell utilities, or interpreter scripts.
  • For repository structure, source, dependencies, callers, and exact file content, use only ast-mcp tools.
  • Use file_capabilities when the supported read or patch methods are uncertain; file_read, run, and file_patch enforce the same result.
  • file_read.mode is agent-selectable: ast returns a source map/requested symbols or RFC 6901-selected structured-document values, text returns a bounded slice, and auto prefers AST. Batch multiple files in one call.
  • Use file_hash for fresh whole-file SHA-256 values without retrieving content.
  • For new files, use only file_write.
  • For existing files, call file_hash immediately before a guarded file_patch; mutation tools declare a files property containing the path-keyed batch.
  • The agent selects file_patch.patchStrategy per target from the effective methods reported by file_capabilities. Prefer ast for structural changes and aider_block for small exact text changes; parseable source commonly supports both.

Available ast-mcp tools

File boundary: file_capabilities, file_hash, file_read, file_write, file_patch, file_chattr, file_delete.

Configuration: config_status, policy_check, document_query, config_core, config_paths.

Code intelligence: digest, map, show, search, find_related, surface, deps, reverse_deps, cycles, graph, callers, callees, trace, impact, context, implements, index, run, squeeze.

Call every intelligence tool directly by name. There is no proxy tool. Use run for bounded AST searches and previews. Direct run rewrites with write: true are a lower-level escape hatch for intentionally bounded cases; they remain first-match-per-file and are not the normal agent patch route. All mutation tools accept a declared files object, are file-operation-root bounded, SHA-guarded where required, and preflight the complete batch before committing any entry. In version 2, access outside the host baseline—including the OS temporary directory—requires an explicit top-level [[paths]] rule; legacy safety.allow_temp_directory and safety.allow_any_path apply only to version 1 configuration. file_write and file_patch share the file_chattr contract rather than independent chmod/chown keys; file_delete is the only directory cleanup capability and only removes empty ancestors after a successful file deletion.

Read the full file on GitHub · 69 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. 5d ago First seen · 69 lines · 1,842 tokens per session scan A 8bb724deb644

Subscribe to this mod's changes

ast-mcp AGENTS.md is an instructions file published in the GitHub repository mwillbanks/ast-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 1,842 tokens to every session, about $0.0092 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.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens