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 managing-parsersgit 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/managing-parsers)<a href="https://agentmods.dev/skills/xberg-io/tree-sitter-language-pack/managing-parsers"><img src="https://agentmods.dev/badge/skills/xberg-io/tree-sitter-language-pack/managing-parsers/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/managing-parsers"><img src="https://agentmods.dev/badge/skills/xberg-io/tree-sitter-language-pack/managing-parsers.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 | $0.00070 | $0.00723 |
| Opus 5 | $0.00035 | $0.00362 |
| Sonnet 5 | $0.00014 | $0.00145 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
managing-parsers 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 12d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managing parsers
Parser libraries download on demand the first time a language is used and are cached on disk. Manage that cache explicitly for offline work, CI prefetch, reproducible builds, or to reclaim space.
Note: parser cache management (
download,clean,init) is done via thets-packCLI directly. The OpenCode tools expose only parse/process/info.
Prefetch (offline / CI)
ts-pack download python rust typescript # specific languages
ts-pack download --all # every available language
ts-pack download --groups all # by group
ts-pack download python --fresh # clean cache first, then download
The manifest currently defines exactly one group, all. Group names are
manifest data, not a fixed list — enumerate them with manifest_groups()
rather than hardcoding. Run download in your CI setup step so later
parse/process calls hit the cache instead of the network.
Inspect
ts-pack list # all available languages
ts-pack list --downloaded # only languages currently cached
ts-pack list --manifest # everything in the remote manifest
ts-pack list --filter script # filter by name substring
ts-pack info python # known? downloaded? cache path?
ts-pack cache-dir # print the effective cache directory
Clean
ts-pack clean # prompts for confirmation
ts-pack clean --force # skip the prompt (use in scripts/CI)
clean removes all cached parser libraries; they re-download on next use.
Config file (init)
ts-pack init writes a language-pack.toml to the current directory
pinning a cache location and/or a language set. This writes a file to
the working directory.
ts-pack init --languages python,rust --cache-dir .ts-pack-cache
Resulting language-pack.toml:
cache_dir = ".ts-pack-cache"
languages = ["python", "rust"]
With no flags, init writes a commented template. When --languages is given,
init also triggers the download for those languages. (init takes only
--languages and --cache-dir — for group-based prefetch use
ts-pack download --groups <names>.) Commit language-pack.toml to pin the
parser set across a team or CI.
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.
- 12d ago First seen · 90 lines · 70 tokens per session scan A bd5ddd783117
managing-parsers is a skill published in the GitHub repository xberg-io/tree-sitter-language-pack (464 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 723 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.