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 chopin789/tool-advisor-skill --skill tool-advisorgit clone --depth 1 https://github.com/chopin789/tool-advisor-skillWrote 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/chopin789/tool-advisor-skill/tool-advisor)<a href="https://agentmods.dev/skills/chopin789/tool-advisor-skill/tool-advisor"><img src="https://agentmods.dev/badge/skills/chopin789/tool-advisor-skill/tool-advisor.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 5.1 | $0.00142 | $0.01080 |
| Opus 5 | $0.00071 | $0.00540 |
| Sonnet 5 | $0.00028 | $0.00216 |
| Haiku 4.5 | $0.00014 | $0.00108 |
Grade A, and why
tool-advisor 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 8d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool Advisor Skill
Helps users get the most out of their Claude Code environment by surfacing relevant tools at the right moment — briefly and without interrupting flow.
Your Job
At the start of handling any substantive task, do a quick mental scan:
- Check installed skills — look at
available_skillsin your system prompt - Check connected MCPs — look at MCP server list in your context
- Check built-in tools — bash, file read/write, web search, image gen, etc.
- Consider uninstalled tools — if a well-known MCP or skill would meaningfully help, mention it
If anything relevant is found that isn't already being used, prepend a 💡 tip to your response.
When to Tip
Tip when there's a specific, actionable match between the task and a tool the user may not be thinking of. Do NOT tip for every response — only when it adds value.
| Task type | Potentially relevant tools to check |
|---|---|
| Creating/editing Word docs | `docx` skill |
| Working with PDFs | `pdf` skill, `pdf-reading` skill |
| Building presentations | `pptx` skill |
| Spreadsheet / data work | `xlsx` skill |
| Reading uploaded files | `file-reading` skill |
| Web research / current events | `web_search` tool, browser MCP |
| Code execution / scripting | `bash` tool |
| Image creation | image generation tools/MCP |
| GitHub / git operations | GitHub MCP |
| Email / calendar / tasks | Gmail, Google Calendar, Asana MCPs |
| Database queries | relevant DB MCPs |
| Building UI / frontend | `frontend-design` skill |
| Hugging Face models/datasets | Hugging Face MCP (check if connected) |
Tip Format
Keep it to 1–2 lines, inline, before your main response. Use this structure:
``` 💡 [Tool name] can help here — [one-sentence reason]. [How to use / install if not installed] ```
Examples:
- `💡 docx skill is available — it'll give you proper Word formatting with TOC and styles.`
- `💡 Hugging Face MCP is connected — you can search and load models directly.`
- `💡 GitHub MCP (not installed) — would let you push this directly to a repo. Install via Claude Code MCP settings.`
- `💡 pdf skill is available — use it to extract text and tables from this PDF properly.`
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.
- 8d ago First seen · 102 lines · 142 tokens per session scan A 32584e14910e
tool-advisor is a skill published in the GitHub repository chopin789/tool-advisor-skill (5 stars, last pushed 5mo ago), licensed MIT. It adds 142 tokens to every session and 1,080 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…