Thomashighbaugh/find-agents
skills/find-agents/SKILL.md
Discover, vet, and install AI agents by searching across agent registries and GitHub. Use when setting up a project (/init-project), when the user asks "find an agent for X", or when you need to extend agent capabilities with specialized subagents. Searches multiple sources simultaneously instead of trusting a single registry.
$ install --global
skillsauthnpx skillsauth add Thomashighbaugh/opencode find-agentsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 27, 2026, 2:28 AM105.3s1 file scanned
SKILL.md
- name:
- find-agents
- description:
- Discover, vet, and install AI agents by searching across agent registries and GitHub. Use when setting up a project (/init-project), when the user asks "find an agent for X", or when you need to extend agent capabilities with specialized subagents. Searches multiple sources simultaneously instead of trusting a single registry.
Find Agents
Find the right agent for a task by searching across agent registries and GitHub simultaneously.
When to Use
- Setting up a project (
/init-project setupor/init-project refresh) - The user asks "find an agent for X" or "is there an agent that does X"
- You need to extend agent capabilities with specialized subagents
- You're about to build a new agent from scratch that a published one might already cover
Multi-Source Search Strategy
| Registry | Search Method | Signal | Blind Spot |
|----------|--------------|--------|------------|
| skills.sh | GET /api/search?q= (filter agent category) | lifetime installs | smaller corpus |
| GitHub topics | gh search repos --topic ai-agent --topic agent-framework --topic autonomous-agent | repo stars, description | repo-level, not agent-level |
| skills.sh API | Fetch and rank by installs | cross-registry validation | newer registries have less data |
How to Choose
Step 1 — Read before you judge. Never recommend from metadata alone. Get the actual agent definition.
Step 2 — Weigh signals in this order:
- Fit — Does the agent's described behavior match the real need?
- Quality signals — Installs/stars, maintenance recency, documentation quality
- Scope — Is it focused or a grab-bag?
- Safety — Check what tools/permissions it requests
Step 3 — Deliver a verdict, not a menu:
- One primary recommendation with why
- 1-2 alternatives framed by need
- If nothing fits, offer to scaffold a custom agent
Installation
For skills.sh agents:
npx skills add <owner>/<repo> --skill <agent-name> -g
For GitHub agents, direct the user to the repo for setup instructions.
Integration with /init-project
This skill is used by /init-project setup and /init-project refresh to:
- Search for agents relevant to the detected project stack and needs
- Present findings for user selection
- Install selected agents
Security & Privacy
- Issues read-only HTTP GETs to public APIs
- Requires no API keys or tokens
- Never auto-installs anything — always user-confirmed
- Check agent permissions before installation — agents run with configured permissions
Related Skills
Thomashighbaugh/tool-creator
tools
VerifiedTrustedCommunity
Create valid, type-safe TypeScript tools for OpenCode — generates correct boilerplate, typed interfaces, and handler stubs. Use when building new tools for global config or per-project .opencode/tools/.
1SKILL.mdUpdated Jul 5, 2026
Thomashighbaugh/tree-of-thoughts
testing
VerifiedTrustedCommunity
Explore multiple solution branches in parallel, evaluate each, and recommend the best path. Use when the user explicitly invokes /ideation tree-of-thoughts or asks for "tree of thought" / "branching exploration".
1SKILL.mdUpdated Jul 1, 2026
Thomashighbaugh/self-consistency
testing
VerifiedTrustedCommunity
Run multiple independent reasoning passes and find consensus. Use when the decision is critically important, the stakes are high, or the user explicitly requests "run it multiple times" / "check consistency" / "self-consistency".
1SKILL.mdUpdated Jul 1, 2026
Thomashighbaugh/opro
testing
VerifiedTrustedCommunity
Optimization by PROmpting — generate candidate prompt variations, test each against a benchmark, and report the best performer. Use when the user invokes /ideation opro or asks for "prompt optimization" / "OPRO".
1SKILL.mdUpdated Jul 1, 2026