tree-sitter-analyzer: Skill for Claude Code

.claude/skills/tsa-deps/SKILL.md

tsa-deps is a skill for Claude Code from aimasteracc/tree-sitter-analyzer. It costs 145 tokens per session (698 once invoked), scanned A, original, MIT.

A code dependency map that shows which files import or are imported by other files. It can also summarize the project's structure, including entry points, central modules, unused-looking modules, and circular dependencies.

In plain words
What is it for?
Use it to inspect a file's dependencies, find modules that many other files rely on, detect circular imports, identify possible entry points, and view the project's import structure.
Why use it?
It avoids opening every file to trace imports manually. This makes it easier to understand unfamiliar code and estimate which files could be affected by a change.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is aimasteracc/tree-sitter-analyzer's own configuration. It tells Claude Code how to work on tree-sitter-analyzer itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tree-sitter-analyzer configures →

Reuse

Borrowing it

Nothing to install: this file belongs to aimasteracc/tree-sitter-analyzer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/aimasteracc/tree-sitter-analyzer/main/.claude/skills/tsa-deps/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/aimasteracc/tree-sitter-analyzer

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.

agentmods badge for tsa-deps

README.md
[![agentmods](https://agentmods.dev/badge/skills/aimasteracc/tree-sitter-analyzer/tsa-deps.svg)](https://agentmods.dev/skills/aimasteracc/tree-sitter-analyzer/tsa-deps)
Your own site
<a href="https://agentmods.dev/skills/aimasteracc/tree-sitter-analyzer/tsa-deps"><img src="https://agentmods.dev/badge/skills/aimasteracc/tree-sitter-analyzer/tsa-deps.svg" alt="Measured on agentmods" height="20"></a>
Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 698 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00145 $0.00698
Opus 5 $0.00072 $0.00349
Sonnet 5 $0.00029 $0.00140
Haiku 4.5 $0.00015 $0.00070

Measured 7d ago against content hash 253b2ee0d7e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

tsa-deps 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 7d 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.

.claude/skills/tsa-deps/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tsa-deps — Imports & module topology

Tool routing

Question Tool
One file's direct deps health action=deps
Project-wide import graph (who imports whom) health action=imports
Project topology (entry points, hubs) structure action=sitemap

Procedure

File-level deps

health action=deps file_path="tree_sitter_analyzer/ast_cache.py" mode="file_deps"
# returns: {imports: [...], imported_by: [...], depth: 2}

mode options:

  • summary — project-wide dependency summary (alias: full)
  • file_deps — one file's graph (requires file_path)
  • blast_radius — impact set for a file (alias: blast; requires file_path)
  • cycles — circular dependencies

Import graph (project-level)

health action=imports language="python" limit=50
# returns: ranked list of import hubs + leaves

Use to find:

  • Hubs (many things import this) — high blast radius if changed
  • Leaves (no one imports this) — possibly dead, or a CLI entry point
  • Cycles — circular imports needing breaking

Sitemap

structure action=sitemap
# returns: {entry_points: [...], hub_modules: [...], leaf_modules: [...]}

Useful as a "first look" right after tsa-landing.

CLI equivalents

uv run tree-sitter-analyzer <file> --dependencies file_deps
uv run tree-sitter-analyzer --dependencies summary
uv run tree-sitter-analyzer --import-graph --import-graph-mode summary
uv run tree-sitter-analyzer --codegraph-sitemap

Anti-patterns

  • DON'T grep for ^import / ^from to build a graph — incomplete (misses conditional / lazy imports captured by the AST)
  • DON'T worry about leaves at the start — they're often legitimate (CLI mains, examples). Focus on hubs.
  • DON'T extract a hub module without first checking its imported_by list — you'll break dozens of callers.

Read the full file on GitHub · 88 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. 7d ago First seen · 88 lines · 145 tokens per session scan A 253b2ee0d7e0

Subscribe to this mod's changes

tsa-deps is a skill published in the GitHub repository aimasteracc/tree-sitter-analyzer (49 stars, last pushed today), licensed MIT. It adds 145 tokens to every session and 698 once invoked, about $0.0007 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 2026-08-30.

Related

Other skills, from other repositories

investigate

Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively invoke this skill (do NOT debug…

GCWing/BitFun · 112 tokens

memstack-development-performance-audit

Use this skill when the user says 'performance audit', 'why is it slow', 'optimize performance', 'page speed', 'Core Web Vitals', 'lighthouse', 'load time', or needs to diagnose and fix frontend or backend performance issues. Do NOT use for code reviews or security audits.

cwinvestments/memstack · 69 tokens

debug

Use this skill to locate a runtime bug. Add targeted instrumentation, collect reproduction evidence, and confirm the root cause before changing code.

GCWing/BitFun · 28 tokens

memorix-troubleshooting

Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.

AVIDS2/memorix · 36 tokens

qa

Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a…

GCWing/BitFun · 160 tokens

papi-verify

Use when the user says "verify", "health check", "check papi", "verify cycle", or after completing all cycle tasks before release. Runs a structured health check on the current PAPI cycle state: plan validity, build state, review coverage, branch hygiene, and data consistency.

getpapi/papi · 63 tokens