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 xberg-io/tree-sitter-language-pack --skill parsing-sourcegit clone --depth 1 https://github.com/xberg-io/tree-sitter-language-packWrote 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/xberg-io/tree-sitter-language-pack/parsing-source)<a href="https://agentmods.dev/skills/xberg-io/tree-sitter-language-pack/parsing-source"><img src="https://agentmods.dev/badge/skills/xberg-io/tree-sitter-language-pack/parsing-source/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/xberg-io/tree-sitter-language-pack/parsing-source"><img src="https://agentmods.dev/badge/skills/xberg-io/tree-sitter-language-pack/parsing-source.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 | $0.00052 | $0.00659 |
| Opus 5 | $0.00026 | $0.00329 |
| Sonnet 5 | $0.00010 | $0.00132 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
parsing-source 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.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parsing source into a syntax tree
ts-pack parse <file> parses one source file with the matching
tree-sitter grammar and prints the resulting concrete syntax tree. Use it
when the user wants the tree itself — to inspect node structure, debug a
grammar, or feed an s-expression to another tool.
Quick recipe
# S-expression (default) — auto-detects language from the file extension
ts-pack parse src/main.rs
# JSON form: { "language", "sexp", "has_errors" }
ts-pack parse src/main.rs --format json
Flag surface
| Flag | Short | Default | Purpose |
|---|---|---|---|
--language <name> |
-l |
auto | Override the language (skip extension detection). |
--format <fmt> |
-f |
sexp |
sexp or json. |
The parser library for the language downloads on first use and is cached.
Language detection
The language is auto-detected from the file extension. Override it when the extension is missing, misleading, or you are reading from stdin:
# Misleading extension or no extension:
ts-pack parse script --language bash
# stdin (use "-" as the file):
cat snippet.py | ts-pack parse - --language python
stdin cannot be auto-detected by path; always pass --language with -.
For content-based detection without a path, use the SDK
(detect_language_from_content) — see the detecting-languages skill.
Output shapes
S-expression
A nested (node_type child ...) tree. Compact, good for eyeballing
structure or piping to a grammar tool.
JSON
{
"language": "rust",
"sexp": "(source_file (function_item ...))",
"has_errors": false
}
Read has_errors to know whether the parse produced any error nodes — a
fast syntax check. For positioned, per-error detail use
ts-pack process <file> --diagnostics (see extracting-code-structure).
Examples
# Inspect a TypeScript file's tree
ts-pack parse src/app.ts
# Machine-readable, then check for syntax errors with jq
ts-pack parse src/app.ts --format json | jq '.has_errors'
# Parse a heredoc as Python
printf 'def f():\n return 1\n' | ts-pack parse - -l python
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.
- 10d ago First seen · 91 lines · 52 tokens per session scan A fbc6289a6fb1
parsing-source is a skill published in the GitHub repository xberg-io/tree-sitter-language-pack (464 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 659 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 2026-08-30.
Other skills, from other repositories
crawlberg
Crawl, scrape, and convert websites to Markdown using the local crawlberg CLI and its MCP server. Use when the user wants to fetch a page, follow links across a domain, enumerate URLs, or drive a real browser. Covers installation, the subcommands (scrape, crawl, map, interact, batch-scrape, batch-crawl, download…
automating-the-browser
Use when extracting a page needs scripted interaction first — click, type, press a key, scroll, wait, screenshot, or run JS before capturing the DOM. Covers crawlberg interact URL --actions with the real action schema, result shape, limits, and external-CDP options.
crawling-a-site
Use when the user wants to follow links across a domain and capture every reachable page as Markdown. Covers crawlberg crawl with depth, page caps, concurrency, rate limiting, domain scoping, robots, and output selection.
headless-fallback
Use when a static fetch returns nothing useful and the page needs a real browser. Covers --browser-mode auto|always|never, external CDP via --browser-endpoint, symptoms of JS-only pages and WAF blocks, and the performance cost.
scraping-html-to-markdown
Use when the user wants a single page rendered as clean Markdown plus structured metadata. Covers crawlberg scrape URL, JSON vs Markdown output, what metadata is returned, and how to handle JS-heavy pages.
serving-the-api
Use when the user wants a long-running HTTP service for scrape/crawl/map instead of one-shot CLI calls or the MCP server — for example wiring crawlberg into other apps over REST. Covers crawlberg serve, the Firecrawl-v1-compatible endpoints, --host/--port, and when to prefer it.