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 GCWing/Sparo-OS --skill find-skillsgit clone --depth 1 https://github.com/GCWing/Sparo-OSWrote 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/gcwing/sparo-os/find-skills)<a href="https://agentmods.dev/skills/gcwing/sparo-os/find-skills"><img src="https://agentmods.dev/badge/skills/gcwing/sparo-os/find-skills/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/gcwing/sparo-os/find-skills"><img src="https://agentmods.dev/badge/skills/gcwing/sparo-os/find-skills.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 | $0.00032 | $0.00679 |
| Opus 5 | $0.00016 | $0.00340 |
| Sonnet 5 | $0.00006 | $0.00136 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
find-skills 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 11d 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.
This is a copy
100% identical to find-skills — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find and Install Skills
Use this skill when users ask for capabilities that might already exist as installable skills, for example:
- "is there a skill for X"
- "find me a skill for X"
- "can you help with X" where X is domain-specific or repetitive
- "how do I extend the agent for X"
Objective
- Understand the user's domain and task.
- Search the skill ecosystem.
- Present the best matching options with install commands.
- Install only after explicit user confirmation.
Skills CLI
The Skills CLI package manager is available via:
npx -y skills <command>
Key commands:
npx -y skills find [query]npx -y skills add <owner/repo@skill> -ynpx -y skills checknpx -y skills update
Reference:
https://skills.sh/
Workflow
1) Clarify intent
Extract:
- Domain (react/testing/devops/docs/design/productivity/etc.)
- Specific task (e2e tests, changelog generation, PR review, deployment, etc.)
- Constraints (stack, language, local/global install preference)
2) Search
Run:
npx -y skills find <query>
Use concrete queries first (for example, react performance, pr review, changelog, playwright e2e).
If no useful results, retry with close synonyms.
3) Present options
For each relevant match, provide:
- Skill id/name
- What it helps with
- Popularity signal (prefer higher install count when shown by CLI output)
- Install command
- Skills page link
Template:
I found a relevant skill: <owner/repo@skill>
What it does: <short description>
Install: npx -y skills add <owner/repo@skill> -y
Learn more: <skills.sh url>
4) Install (confirmation required)
Only install after user says yes.
Recommended install command:
npx -y skills add <owner/repo@skill> -g -y
If user does not want global install, omit -g.
5) Verify
After installation, list or check installed skills and report result clearly.
When no skill is found
If search returns no good match:
- Say no relevant skill was found.
- Offer to complete the task directly.
- Suggest creating a custom skill for recurring needs.
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.
- 11d ago First seen · 109 lines · 32 tokens per session scan A 0e3699b7965c
find-skills is a skill published in the GitHub repository GCWing/Sparo-OS (20 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 679 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to find-skills, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
memory-consolidation
Weekly synthesis of accumulated notes and memory optimization.
systematic-debug
4-phase root cause analysis and debugging.
backup-skill
Creates and manages backup snapshots.
brainstorming
Socratic design refinement and ideation.
code-review
Automated code review with checklist and quality gates.
content-draft
Blog/newsletter/content writing skill.