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/nikuscs/scanr/ts-code-scannpx skills add nikuscs/scanr --skill ts-code-scangit clone --depth 1 https://github.com/nikuscs/scanrWhat 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 | $0.00034 | $0.01033 |
| Opus 5 | $0.00017 | $0.00517 |
| Sonnet 5 | $0.00007 | $0.00207 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade A, and why
ts-code-scan 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 2d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
If scanr is missing: brew install nikuscs/tap/scanr. Presenting findings to a human → REPORTING.md.
For any folder, run one inventory (not verbose, not compact, not head):
scanr scan --mode inventory --root <path>
Done when stats.parsed == stats.files and stats.errors == 0. List nonzero skipped/errors. Then answer from the JSON keys below. Add --lines only if the user wants line numbers.
Get all constants
Use constants. Each row is {file, name, kind} where kind is primitive or arrow (const Foo = () => {} is arrow).
Counts: constants.length, split by kind. A “quick list” is the names, or UPPER_SNAKE names if they want real constants not hook locals.
Get all types
Use types. Each row is {file, name, kind} where kind is interface or type.
Get all functions / components / hooks / classes / enums / exports
Same inventory JSON:
functions— named functions (dotted if nested)components— React components (.tsx+ JSX + Uppercase)hooks— declarations nameduse+ uppercase, notuseStatecallsclassesenumsexports
Get a tree
scanr tree --root <path>
--path <subdir> to focus. --functions for function markers. --function-details when they want nested components/functions explained. --health --only-findings --top 20 for hotspots. Return the command output as printed.
Usages of a name
scanr refs <name> --root <path>
Name-level oxc + import remapping, not tsserver. Usages exclude the declaration line.
Rename a symbol
scanr rename <Name> <NewName> --root <path>
scanr rename src/card.tsx#Name <NewName> --root <path> # when the bare name is ambiguous
Type-accurate via the TypeScript language service: imports, exports, aliases (public names preserved), barrels, JSX, interface/enum members, dynamic imports. Requires bun or node on PATH and a tsconfig.json (--tsconfig <path> when not at the root). --dry-run prints planned files and writes nothing.
What ships with it
1 file 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.
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.
- 2d ago First seen · 82 lines · 34 tokens per session scan A d811507d70e9
ts-code-scan is a skill published in the GitHub repository nikuscs/scanr (10 stars, last pushed 7d ago), licensed MIT. It adds 34 tokens to every session and 1,033 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
vector-collection-management
Create, populate, list, and delete vector-store collections through the vector-mcp MCP server's vectorcollectionmanagement tool. Use when the agent must stand up a new RAG collection, ingest documents (from a directory, file paths/URLs, or raw text) into an existing collection, enumerate collections, or drop one …
vector-databases
Vector database operations — embed, store, search, and build RAG pipelines.
ai-rag-pipeline-architect
Activate when architecting, implementing, or optimizing Retrieval-Augmented Generation (RAG) systems, semantic vector search, document chunking, hybrid search, and reranking pipelines — trigger phrasings include "build a RAG pipeline for my documents", "how do I chunk PDFs for vector search", "setup pgvector in…
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.
uteke-memory
Persistent memory engine for AI agents via the uteke CLI — remember, recall, search, forget with semantic + FTS5 hybrid search, documents, knowledge graph, rooms, tiered memory, and multi-agent namespaces.