agentmods.dev

ast-mcp

ast-mcp is a skill for Codex from mwillbanks/ast-mcp. It costs 60 tokens per session (2,814 once invoked), scanned A, original, MIT.

A code-exploration and file-management tool that understands source code structure and controls how files are read or changed.

In plain words
What is it for?
Finding symbols, mapping files, checking dependencies, reading and hashing files, creating files, and patching existing code.
Why use it?
It gives agents a consistent way to inspect unfamiliar code, trace relationships, and make edits while enforcing specific write rules.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex; built for aider.

not rated 0repo 3d ago A scan 60 tokens original MIT

Good fit Finding symbols, mapping files, checking dependencies, reading and hashing files, creating files, and patching existing code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mwillbanks/ast-mcp/ast-mcp
View source ↗ mwillbanks/ast-mcp mwillbanks.github.io
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.

Any agent
npx skills add mwillbanks/ast-mcp --skill ast-mcp
Clone the repo
git clone --depth 1 https://github.com/mwillbanks/ast-mcp

Made for: Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/mwillbanks/ast-mcp/ast-mcp/github.svg)](https://agentmods.dev/skills/mwillbanks/ast-mcp/ast-mcp)
Your own site
<a href="https://agentmods.dev/skills/mwillbanks/ast-mcp/ast-mcp"><img src="https://agentmods.dev/badge/skills/mwillbanks/ast-mcp/ast-mcp/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 ast-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/mwillbanks/ast-mcp/ast-mcp"><img src="https://agentmods.dev/badge/skills/mwillbanks/ast-mcp/ast-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,814 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00060 $0.02814
Opus 5 $0.00030 $0.01407
Sonnet 5 $0.00012 $0.00563
Haiku 4.5 $0.00006 $0.00281

Measured 10d ago against content hash 1d83c76a1568, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ast-mcp 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 10d ago.

The scan reads SKILL.md. This mod also ships 13 executable files (evals/measure.ts, evals/score.test.ts, evals/score.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

templates/skills/ast-mcp/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AST MCP

Treat ast-mcp as the only code-intelligence and filesystem boundary. Do not call direct editors, apply_patch, shell mutation utilities, or interpreter write scripts.

Start with availability

  1. Confirm that file_hash, file_read, file_write, file_patch, and the direct intelligence tools are callable.
  2. If any are unavailable, stop mutation and follow installation.md. Run scripts/check-install.ts to diagnose the configured host when Bun and this skill directory are available.
  3. After installation, ask the host to reconnect or restart MCP servers, then list tools again. Never fall back to another writer.

Explore before editing

  • Start unfamiliar work with digest, use map for one file's shape, and use show for exact symbols. When a file workflow is uncertain, call file_capabilities once for all relevant paths; file_read, run, and file_patch enforce that same result.
  • Use search when names are unknown and find_related for code similar to a known location.
  • Use context for a symbol plus nearby calls; use impact before changing a public or shared symbol.
  • Use deps, reverse_deps, graph, or cycles for module relationships.
  • Use callers, callees, or trace for execution flow; use implements for type hierarchies.
  • Use surface for exported API shape, index for search-index maintenance, and squeeze only for repetitive logs or text.
  • file_read accepts an agent-selected mode: ast returns a source map/requested symbols or RFC 6901-selected structured-document values, text returns a bounded zero-based end-exclusive slice, and auto prefers AST when supported. Use symbols for source and selectors for JSON, JSONC, TOML, or YAML. Text mode remains available for AST-capable files when exact source text is necessary. Batch multiple files in one call.
  • Use ast-mcp intelligence as the primary repository search route. Never invoke ast-grep directly and never use sed for repository reads or edits. rg is permitted only as a discouraged fallback for exact literals, identifiers, non-AST formats, or discovery unavailable through ast-mcp; external transcript analysis, Git metadata, validation, and live-runtime reproduction are exceptions.

Read the full file on GitHub · 143 lines

Files

What ships with it

22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 143 lines · 60 tokens per session scan A 1d83c76a1568

Subscribe to this mod's changes

ast-mcp is a skill published in the GitHub repository mwillbanks/ast-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 60 tokens to every session and 2,814 once invoked, about $0.0003 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.

Debugging
Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens