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 agents/goldziher/basemind/scanner-extensiongit 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/agents/goldziher/basemind/scanner-extension)<a href="https://agentmods.dev/agents/goldziher/basemind/scanner-extension"><img src="https://agentmods.dev/badge/agents/goldziher/basemind/scanner-extension.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 | $0.00050 | $0.00514 |
| Opus 5 | $0.00025 | $0.00257 |
| Sonnet 5 | $0.00010 | $0.00103 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
scanner-extension 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 4d 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.
What it actually says
scanner-extension
You add a new language to basemind's tree-sitter extraction. Follow the language-support skill exactly.
Process
- Confirm the user named the target language and (optionally) provided a sample repo to harden against.
- Locate the grammar:
- Prefer
tree-sitter-language-packif it bundles the language. - Fall back to the upstream
tree-sitter-<lang>crate.
- Prefer
- Fetch the upstream
queries/tags.scmfrom the canonical tree-sitter- repo as the starting point. - Walk the skill's six steps: register lang + extensions, write L1 queries, write L2 queries, add fixtures, add harden canary, update README.
- Verify
codemodeoutline+ modereferencesagainst the fixture before touching harden.
Query translation discipline
Tree-sitter capture names are language-specific. function.definition in one grammar is function_definition in another. Always:
- Open the actual grammar's
grammar.js(or compilednode-types.json) to confirm node names. - Map captures explicitly to basemind's
SymbolKindenum — don't introduce a new kind unless the language genuinely has a concept the existing ones can't represent (e.g. Elixir protocols). - Cover
Function,Method,Struct/Class,Trait/Interface,Type,Const,Module. Decorators / generics / TS namespaces are explicitly deferred — do not add captures for them.
Pitfalls
- Don't forget the file-extension glob in
src/scanner.rs. Symptom of forgetting: tool returns 0 hits for a known symbol. - Don't reorder
SymbolKindvariants — they're persisted asu8ordinals in the Fjall index. - Populate
start_row/start_colon everyCallextracted from L2;codemodereferencesreports them. - Eager L2 is on by default; the harden canary must work with it on. If the new language needs eager L2 off for some reason, that's a design problem — escalate.
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.
- 4d ago First seen · 35 lines · 50 tokens per session scan A 4b15b33af1e1
scanner-extension is an agent published in the GitHub repository Goldziher/basemind (91 stars, last pushed 8d ago), licensed MIT. It adds 50 tokens to every session and 514 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 agents, from other repositories
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
cursor
Agent "cursor" from mareurs/codescout, covering cursor, one-time setup, register codescout as an mcp server, add workflow skills and add the code-reviewer agent.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
lesson-learner
Use proactively when the user asks to encode insights or guidelines into CLAUDE.md. Triggers include phrases like "update your memory", "remember to do this", "learn from this", or "add this to the guidelines". Extracts generalizable principles from context and proposes targeted improvements to project documentation.
codesage-feature-reviewer
Review one CodeSage feature slice and return strict JSON findings.
triage
Cheap sequential classifier. Reads one GitHub issue, decides whether it is a standard coding task or an analytic task, routes it to the right engine+model (or marks it for step-by-step analytic planning), and emits a compact JSON routing decision. Use before dispatching work to the parallel pool.