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/mwillbanks/ast-mcp/agents-mdgit clone --depth 1 https://github.com/mwillbanks/ast-mcpWrote 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.
[](https://agentmods.dev/instructions/mwillbanks/ast-mcp/agents-md)<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>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.
| Model | Per session | Once 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 |
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.
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-mcpskill 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_capabilitieswhen the supported read or patch methods are uncertain;file_read,run, andfile_patchenforce the same result. file_read.modeis agent-selectable:astreturns a source map/requested symbols or RFC 6901-selected structured-document values,textreturns a bounded slice, andautoprefers AST. Batch multiple files in one call.- Use
file_hashfor fresh whole-file SHA-256 values without retrieving content. - For new files, use only
file_write. - For existing files, call
file_hashimmediately before a guardedfile_patch; mutation tools declare afilesproperty containing the path-keyed batch. - The agent selects
file_patch.patchStrategyper target from the effective methods reported byfile_capabilities. Preferastfor structural changes andaider_blockfor 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.
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.
- 5d ago First seen · 69 lines · 1,842 tokens per session scan A 8bb724deb644
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.
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.
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).
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.
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.
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).