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 skills add oaustegard/claude-skills --skill tree-sittinggit clone --depth 1 https://github.com/oaustegard/claude-skillsWrote 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/skills/oaustegard/claude-skills/tree-sitting)<a href="https://agentmods.dev/skills/oaustegard/claude-skills/tree-sitting"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/tree-sitting/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.
<a href="https://agentmods.dev/skills/oaustegard/claude-skills/tree-sitting"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/tree-sitting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00184 | $0.02632 |
| Opus 5 | $0.00092 | $0.01316 |
| Sonnet 5 | $0.00037 | $0.00526 |
| Haiku 4.5 | $0.00018 | $0.00263 |
Grade A, and why
tree-sitting 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.
How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tree-sitting
AST-powered code navigation using tree-sitter. Each invocation auto-scans the codebase (~700ms for 250 files), then runs queries at sub-millisecond speed.
Setup
uv pip install --system --break-system-packages tree-sitter
Grammars are loaded from bundled parsers/*.so files — no network fetch,
no tree-sitter-language-pack dependency. Install is <1s.
Verify the install before trusting an empty result. Without the
tree-sitter core package the CLI parses nothing, prints no error, and exits
0. Run --stats on a directory you know contains code; a missing dependency
looks like this:
Scanned 0 files (0 KB) in 0ms
Symbols: 0 | Languages:
No files scanned.
Zero symbols where you expect code means the dependency is missing, not that
the code is empty. Reinstall and re-run before concluding anything from the
output. There is no Errors: line in this case — that line appears only when
a parse fails, and an absent parser never gets that far. Measured 2026-08-24 by
blocking the import and re-running.
When NOT to use this skill
Reach for the neighbour instead when the task is one of these. Every row is a
skill this one is routinely confused with; a 2026-08-24 retrieval measurement
over the 92-skill pool put tree-sitting outside the top-1 slot on all five of
its own canonical queries, losing them to accessing-github-repos,
featuring, searching-codebases and cloning-project.
| Task | Use instead |
|---|---|
| The repo is not on local disk yet | accessing-github-repos, then come back |
| "What does this repo DO?" — capabilities, not symbols | featuring |
| First-encounter orientation on an unfamiliar repo | exploring-codebases (it calls this skill in step 2) |
| Teaching a human the codebase through exercises | orienting-codebases |
| ALL true callers of a Python symbol, binding-resolved | searching-codebases (--refs; pyright excludes same-named false positives) |
| Ranking files by relevance to a multi-word concept | bm25 |
| A literal string, regex, or any non-symbol text match | plain rg — faster and equally accurate |
What ships with it
11 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.
- CHANGELOG.md 4.4 KB
- README.md 1.3 KB
- scripts/engine.py 74 KB runs code
- scripts/server.py 6.5 KB runs code
- scripts/treesit.py 14 KB runs code
- tests/test_cache_fingerprint.py 12 KB runs code
- tests/test_cache_lazy_source.py 10 KB runs code
- tests/test_cache_lifecycle.py 30 KB runs code
- tests/test_cache_roundtrip.py 19 KB runs code
- tests/test_cli_cache.py 15 KB runs code
- tests/test_engine.py 19 KB runs code
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.
- 7d ago First seen · 220 lines · 184 tokens per session scan A a6cc93ecb944
tree-sitting is a skill published in the GitHub repository oaustegard/claude-skills (148 stars, last pushed yesterday), licensed MIT. It adds 184 tokens to every session and 2,632 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
handoff-by-caio
Generates a structured Markdown handoff file to move an active conversation into a new chat, preserving full context, decisions, artifacts, and a ready-to-paste resume prompt. ALWAYS trigger this skill when the user says "move to a new chat", "move this to a new chat", "handoff", "/handoff", "continue in a new chat"…
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so Claude can answer questions on your team's behalf. Team-scope sibling to second-brain (which is personal-scope). Seven modes — capture (drop something into the right structured dir), compile (process into wiki…
slide-deck
When you want to draft, update, convert, or export a slide deck for a React/Next.js slide system (${SLIDEDECKREPO:-$HOME/code/your-slide-deck-site}/src/app/slides/). Writes TypeScript Slide[] arrays using your primitives (Eyebrow, Heading, Accent, Body, BulletList, Divider, TwoCol, GradientText), 12 cycling brand…
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…
session-cleanup
Identify stale and empty Claude Code sessions in the Agent Monitor and explain the cleanup endpoint (POST /api/settings/cleanup), always showing the exact list of what WOULD be removed before anything is deleted. Cleanup permanently deletes data, so this skill previews first and requires explicit user confirmation.…
toolify
When you want to integrate an external tool, API, MCP server, or service into a project — the wizard walks you through auth, config, env vars, client wrapper code, example usage, and (optionally) a smoke-test. Scoped to Next.js and Rails projects (the two primary stacks). Interactive Q&A pattern — starts with the tool…