Borrowing it
Nothing to install: this file belongs to rajbos/ai-engineering-fluency. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rajbos/ai-engineering-fluency/main/.claude/skills/improve-tool-families/SKILL.mdgit clone --depth 1 https://github.com/rajbos/ai-engineering-fluencyWrote 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/rajbos/ai-engineering-fluency/improve-tool-families)<a href="https://agentmods.dev/skills/rajbos/ai-engineering-fluency/improve-tool-families"><img src="https://agentmods.dev/badge/skills/rajbos/ai-engineering-fluency/improve-tool-families/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/rajbos/ai-engineering-fluency/improve-tool-families"><img src="https://agentmods.dev/badge/skills/rajbos/ai-engineering-fluency/improve-tool-families.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00109 | $0.01300 |
| Opus 5.5 | $0.00044 | $0.00520 |
| Sonnet 5.5 | $0.00022 | $0.00260 |
| Haiku 4.5 | $0.00011 | $0.00130 |
Grade A, and why
improve-tool-families 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 yesterday.
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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve Tool Families Skill
The "Tool Output Token Analysis" tab in the VS Code extension groups tool
calls into families (File Reading, File Writing, Search & Discovery,
Shell / Terminal, Code Intelligence, Web & Research, ...) so a "built-in"
tool's token efficiency can be compared against "alternative" tools that do
the same job. That grouping comes from DEFAULT_TOOL_FAMILIES in
src/toolFamilies.ts, merged with any user overrides in the
aiEngineeringFluency.toolFamilies VS Code setting.
The matching is an exact string match against the raw tool name recorded
per editor (see src/adapters/*.ts and usageAnalysis.ts writing into
toolCalls.byTool/outputTokensByTool) — there is no cross-editor
normalization step first. That means every spelling a different editor/agent
uses for "read a file", "run a shell command", "search text", etc. must be
listed explicitly, or it silently falls into the generic "Other Tools"
bucket instead of being compared.
What the script does
analyze-tool-families.js:
- Loads the canonical set of known tool names from
src/toolNames.json(the cross-editor tool-name → friendly-name map used elsewhere in the repo) and/or an ad-hoc list passed via--tools. - Parses
DEFAULT_TOOL_FAMILIESout ofsrc/toolFamilies.ts(no build step needed). - Reports which candidate tool names are not yet covered by any
family's
builtIn/alternativesarrays. - Suggests a likely family for each uncovered name using keyword
heuristics (e.g. names containing
read/view→reading,grep/glob/search→search,run/terminal/bash→shell,web/fetch→web, etc.).
It does not edit toolFamilies.ts automatically — deciding whether a
tool is a plain "builtIn" (baseline) tool or a more token-efficient
"alternative" is a judgment call that needs a human/agent to review the
tool's actual behavior, not just its name.
Usage
# Compare against every name in src/toolNames.json
node .github/skills/improve-tool-families/analyze-tool-families.js
# Also check specific tool names (e.g. the current agent session's own tool list)
node .github/skills/improve-tool-families/analyze-tool-families.js --tools view,edit,grep,glob,powershell,web_fetch,ask_user
# Machine-readable JSON (for further processing)
node .github/skills/improve-tool-families/analyze-tool-families.js --json
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.
- yesterday First seen · 103 lines · 109 tokens per session scan A d5a20cbf06a1
improve-tool-families is a skill published in the GitHub repository rajbos/ai-engineering-fluency (119 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 1,300 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-26.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…