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 PaulRBerg/agent-skills --skill tool-findergit clone --depth 1 https://github.com/PaulRBerg/agent-skillsWrote 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/paulrberg/agent-skills/tool-finder)<a href="https://agentmods.dev/skills/paulrberg/agent-skills/tool-finder"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/tool-finder/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/paulrberg/agent-skills/tool-finder"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/tool-finder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.00588 |
| Opus 5.5 | $0.00016 | $0.00235 |
| Sonnet 5.5 | $0.00008 | $0.00118 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
tool-finder 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 17d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool Finder
This skill is coordination-exempt: skip the ai-coord gate for its declared work.
Recommend the current option that best fits the user's actual constraints, backed by fresh primary evidence.
Workflow
- Infer the ecosystem, existing stack, must-haves, switching cost, and decision criteria from the request and repository. Ask only when an unknown would materially change the recommendation.
- Check whether the standard library, platform, or an already-installed tool is sufficient before adding a dependency.
- Search current authoritative sources. Read references/tool-finder.md only for the relevant ecosystem's source routing, fallback criteria, install conventions, and red flags. Issue independent lookups for different candidates (registry, repository, advisories, changelog) together in one turn.
- Compare the viable options against the user's criteria. Use adoption, maintenance, security, documentation, performance, operational cost, and ecosystem fit only where they affect this decision. Do not force fixed weights or a fixed number of candidates.
- Recommend one option when the evidence supports it. State the decisive tradeoff, material red flags, and the closest alternative. Say when the evidence is too close or no external tool is justified.
Defaults
- With no repository evidence, default to JavaScript/TypeScript and Node.js tooling.
- For JavaScript installs, prefer the repository's package manager and otherwise
ni. For macOS CLIs, prefer an official or well-maintained Homebrew formula. - Prefer registries, official docs, repositories, changelogs, and security advisories over secondary comparisons. For agent skills, search registries and GitHub because no single index is complete.
Completion
The answer is complete when the recommendation is traceable to current sources, the deciding criteria are explicit, installation guidance matches the user's environment, and uncertainties or disqualifying risks are visible. Use a table only when repeated fields make the comparison easier to scan.
What ships with it
2 files 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.
- 17d ago Changed · +1 lines 019ecb9398aa
- 1mo ago Changed f0e3f8d20565
- 2mo ago First seen · 47 lines · 39 tokens per session scan A 915c7b3422fd
tool-finder is a skill published in the GitHub repository PaulRBerg/agent-skills (104 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 588 once invoked, about $0.0002 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 2026-08-30.
tool-finder compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tool-finderPaulRBerg/agent-skills | Skill | 104 | 2d ago | MIT | A | 39 | Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 2d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 5d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |