A local code-navigation plugin that uses the program's syntax tree and relationships between code layers to locate exact lines, affected areas, and related tests. An abstract syntax tree is a structured representation of source code.

Use it to find precise code locations, estimate the impact of a change, and identify tests that cover the affected code.

It helps an agent inspect only relevant code instead of loading large amounts of unrelated context.

ast-graph — Plugin for Claude Code by davenportjw/agent-skills

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.

Clone the repo

git clone --depth 1 https://github.com/davenportjw/agent-skills

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/davenportjw/agent-skills/ast-graph/github.svg)](https://agentmods.dev/plugins/davenportjw/agent-skills/ast-graph)

Your own site

<a href="https://agentmods.dev/plugins/davenportjw/agent-skills/ast-graph"><img src="https://agentmods.dev/badge/plugins/davenportjw/agent-skills/ast-graph/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/davenportjw/agent-skills/ast-graph"><img src="https://agentmods.dev/badge/plugins/davenportjw/agent-skills/ast-graph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 1 skill, 2 hooks, 1 MCP server cost 144 tokens a session between them.

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.

Security

Grade A, and why

ast-graph 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 6d 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.

plugins/ast-graph/.claude-plugin/plugin.json · 13 lines

What it actually says

{
  "name": "ast-graph",
  "version": "1.0.0",
  "description": "Local AST & cross-layer code graph plugin that cuts agent context token usage by jumping straight to exact line spans, blast radius, and covering tests.",
  "author": {
    "name": "Jason Davenport",
    "url": "https://github.com/davenportjw"
  },
  "repository": "https://github.com/davenportjw/agent-skills",
  "license": "Apache-2.0",
  "keywords": ["ast", "sqlite", "graph", "lineage", "mcp", "code-search"]
}

Contents

What it installs

The manifest is a name and a version. 1 skill, 2 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 144 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json 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.

marketplace.json 605 B

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.

6d ago Changed · +7 lines cbe669f61448
14d ago First seen · 6 lines scan A 4879610fab75

Subscribe to this mod's changes

ast-graph is a plugin published in the GitHub repository davenportjw/agent-skills (4 stars, last pushed 2d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-30.

Code review Debugging

ast-graph next to 6 plugins from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ast-graphdavenportjw/agent-skills	Plugin	4	2d ago	Apache-2.0	A	—	Claude Code
gaussian-engineeringjaccen/Awesome-Gaussian-Skills	Plugin	184	today	Apache-2.0	A	—	Claude Code
graph-it-livemagic5644/Graph-It-Live	Plugin	63	today	MIT	A	—	Claude Code
code-reviewccplugins/awesome-claude-code-plugins	Plugin	1.0k	3mo ago	Apache-2.0	A	—	Claude Code
kinfirelock-ai/kin	Plugin	68	1mo ago	Apache-2.0	A	—	Gemini CLI
memtrace-skillssyncable-dev/memtrace-public	Plugin	516	today	none	A	—	Claude Code
hunchdavesheffer/hunch	Plugin	17	today	none	A	—	Claude Code