Skip to content
Back to skills

Ls Agent Capability Routing

ASecurity

Use when choosing a LocalSetup Agent-* lane for exploration, research, bounded implementation, or review. Consult the static capability matrix; do not probe account or network availability.

  • 6 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 7, 2026
ai-agentspythonbash

Works with

  • cli

Security analysis

A100/100

Pro scans all 7 files and shows the line behind each finding

Scanned November 7, 2026

npx -y skills add CruxExperts/LocalSetup --skill ls-agent-capability-routing --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ls Agent Capability Routing?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Ls Agent Capability Routing
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/cruxexperts-ls-agent-capability-routing/badge)](https://www.skillsdirectory.com/skills/cruxexperts-ls-agent-capability-routing)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: ls-agent-capability-routing
description: Use when choosing a LocalSetup Agent-* lane for exploration, research, bounded implementation, or review. Consult the static capability matrix; do not probe account or network availability.
metadata:
  version: "1.0"
---

# LocalSetup Agent Routing

Use this skill when a bounded task needs a deterministic, reviewed `Agent-*`
lane recommendation. The selector reads only its bundled matrix and writes a
share-safe JSON receipt. It does not select a client model, effort, permission,
or worker configuration.

## Select a lane

Provide a closed JSON request on standard input or in a file:

```bash
python3 scripts/agent_routing.py select --request request.json
```

```bash
printf '%s' '{"schema":"agent_routing_request_v1","task_class":"routine","risk":"low","required_capabilities":[]}' \
  | python3 scripts/agent_routing.py select --request -
```

Treat `rejected` and `offline` receipts as typed results. Do not add a model,
price, account, observation, permission, or Ultra override to the request.
Request input is limited to 65,536 UTF-8 bytes; oversized, unavailable, or
malformed input is returned as a rejected `invalid_request` receipt after the
bundled resource passes validation. Resource validation runs first, so an invalid
or expired resource returns `resource_invalid` or `resource_stale` without
reading or classifying the request.

## Boundaries

- The matrix is static reviewed evidence. Unknown capability evidence never
  satisfies a request.
- `fresh_until` is the repository's local review-expiry policy, not an upstream
  freshness guarantee.
- `Agent-*` is a LocalSetup routing-policy label, not a provider model claim.
- The selector is read-only and does not inspect runtime availability or
  observations.

Files in this skill

  • SKILL.md1.7 KB
  • resources/model-capability-matrix/manifest.json1.6 KB
  • resources/model-capability-matrix/schema.json2.9 KB
  • resources/model-capability-matrix/snapshot.json4.1 KB
  • schemas/routing-receipt.schema.json2 KB
  • schemas/routing-request.schema.json593 B
  • scripts/agent_routing.py27.7 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.