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 agentmods add skills/goldziher/basemind/language-supportnpx skills add Goldziher/basemind --skill language-supportgit clone --depth 1 https://github.com/Goldziher/basemindWrote 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/goldziher/basemind/language-support)<a href="https://agentmods.dev/skills/goldziher/basemind/language-support"><img src="https://agentmods.dev/badge/skills/goldziher/basemind/language-support.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00006 | $0.00651 |
| Opus 5 | $0.00003 | $0.00326 |
| Sonnet 5 | $0.00001 | $0.00130 |
| Haiku 4.5 | $0.00001 | $0.00065 |
Grade A, and why
language-support 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 5d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Language Support
Use this to add a new language to basemind's extraction. Supported languages today include Rust, Python, TypeScript/JSX, JavaScript, Go.
Inputs needed
- A tree-sitter grammar crate (e.g.
tree-sitter-elixir) reachable via thetree-sitter-language-packumbrella crate basemind already depends on, or as a direct dep. - The grammar's upstream
queries/tags.scmfrom the tree-sitter org repo — it's the canonical starting point for symbol + reference extraction.
Steps
-
Register the language
- Add the lang ID + file extensions to
src/lang.rs's language registry. - Add the extensions to the scanner's accepted-extension set in
src/scanner.rs(or the central glob if one exists).
- Add the lang ID + file extensions to
-
L1 (outline) queries
- Adapt the upstream
tags.scmto basemind's L1 capture shape:@symbol.function,@symbol.method,@symbol.class, etc. mapped toextract::SymbolKind. - Place query string in
src/queries/<lang>.rs(or undersrc/extract/queries/, matching the existing layout). - Wire into
extract::l1::extract's language dispatch.
- Adapt the upstream
-
L2 (calls) queries
- Add a call query: callees as
@call.calleeplus optional receiver / type info. - Wire into
extract::l2::extract's dispatch. Remember to populatestart_row/start_colonCall.
- Add a call query: callees as
-
Fixtures + smoke test
- Add a synthetic file under
tests/fixtures/<lang>/exercising at least: one function def, one method, one call site, one import. - Add assertions in
tests/mcp_smoke.rs(or a newtests/<lang>_smoke.rs) coveringcodemodeoutline+ modereferencesfor the fixture.
- Add a synthetic file under
-
Harden harness canary
- Pick a real OSS repo for the language (criteria: stable, ≥ a few hundred files, well-known canary symbols). Add to the repo list in
tests/harden.rswith a clone URL + optional--depth. - Add a
>= Ncanary assertion (codemodereferencesor modesymbols) — see theharness-canary-authoringskill.
- Pick a real OSS repo for the language (criteria: stable, ≥ a few hundred files, well-known canary symbols). Add to the repo list in
-
README
- Update the supported-languages list with the new language and file extensions.
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.
- 5d ago First seen · 46 lines · 6 tokens per session scan A a3b3e6306003
language-support is a skill published in the GitHub repository Goldziher/basemind (98 stars, last pushed 3d ago), licensed MIT. It adds 6 tokens to every session and 651 once invoked, about $0.0000 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
debug-evals
Debug haiku.rag evaluation runs in Logfire. Use when asked to look at Logfire for an eval run, find failing or low-scoring eval cases, compare runs, check citation quality (citedmap) or judge pass rate (answerequivalent), or explain why an eval case failed. Drives the Logfire MCP against the evals service, or the…
projectatlas
Use ProjectAtlas as the atlas-first orientation layer before broad source reads, with MCP-first task startup, short-alias worktree registration and routing, safe targeted initialization, ranked navigation, exact or federated graph evidence, purpose curation, health, lint, and repository-wide token reporting.
codex-coding-plugin
Build, review, or fix ProjectAtlas plugin/runtime installer integration for Codex, Claude Code, and OpenCode, especially version convergence, stale ProjectAtlas cache repair, MCP config generation, skill artifacts, host smoke tests, and fake-host tests for ProjectAtlas releases.
research
Performs deep research on a topic via deepresearch. Simulates a multi-step research process and returns a comprehensive research result as a string.
change-review
Use when reviewing a set of changes before they merge — a PR, a branch diff, or the working-tree changes you just made — in a Repowise-indexed codebase (.repowise/ directory exists). Activates for "review this PR", "is this safe to merge", "what's the blast radius of these changes", "did I miss anything", or "what…
lsp-refactor
End-to-end safe refactor workflow — blast-radius analysis, speculative preview, apply to disk, verify build, run affected tests. Inlines lsp-impact + lsp-safe-edit + lsp-verify + lsp-test-correlation into one coordinated sequence.