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 agentmods add skills/qwerfunch/cladding/routenpx skills add qwerfunch/cladding --skill routegit clone --depth 1 https://github.com/qwerfunch/claddingWhat 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 | $0.00087 | $0.00445 |
| Opus 5 | $0.00044 | $0.00222 |
| Sonnet 5 | $0.00017 | $0.00089 |
| Haiku 4.5 | $0.00009 | $0.00044 |
Grade A, and why
route 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 2d 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.
What it actually says
Cladding route
Run clad route <prompt> from anywhere — the verb is read-only and does not require a workspace. It calls classifyIntent(prompt) from src/router/intent.js and emits the resolved verb name as a Pulse note. Exit code is 0 on a confident match and 1 when the intent resolves to unknown.
clad route "scan my codebase and write the conventions doc"
clad route "is the LLM host healthy?"
clad route "I'm stuck, what's next?"
The verb is the smallest surface that exercises the router in isolation. Production callers typically reach the router indirectly through the orchestrator persona (src/agents/orchestrator.md) or through clad_route over MCP.
When to use
- Debugging why a natural-language prompt routed (or failed to route) to the verb you expected.
- Confirming a new verb's intent patterns are reachable after adding them to
src/router/intent.js. - Smoke-testing the router during local development before publishing a plugin update.
The classifier is intentionally conservative — when no rule matches strongly enough, the result is unknown and the verb exits 1 so callers can fall back to an explicit verb lookup instead of guessing.
Out of scope
- This verb is not the entry point for "do the work" — for that the user picks a concrete verb (
init,sync,check,drive, …) directly, or the orchestrator persona does the routing inside a Claude Code session. - Free-form prompts that span multiple verbs (
"sync then check then drive") collapse to whichever single verb best matches; the router does not split intent.
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.
- 2d ago First seen · 29 lines · 87 tokens per session scan A 5958830fef28
route is a skill published in the GitHub repository qwerfunch/cladding (14 stars, last pushed 4d ago), licensed MIT. It adds 87 tokens to every session and 445 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
map-auto
Single-entry autonomous autopilot: routes a task through the existing MAP workflows via routetask, then drives the selected chain (map-plan -> map-efficient -> map-check -> map-review, as routed) end-to-end to a committed feature branch in one session, auto-approving routine workflow-control holds and hard-stopping on…
map-resume
Resume an interrupted MAP workflow from .map/ /stepstate.json checkpoint. Use when returning after context exhaustion, /clear, or a session crash mid-workflow. Do NOT use to start new work; use map-plan or map-efficient.
map-skill-eval
Evaluate a /map- skill's trigger accuracy and cost. Use when asked to measure skill trigger accuracy, run an eval-set, or check token/duration cost via mapify skill-eval. Do NOT use to plan or implement; use map-plan or map-efficient.
skills-management
Search, find, discover, install, remove, update, review, deduplicate, list, move, optimise, and iterate on skills for AI coding agents. Use when user asks "find a skill for X", "install skill", "remove skill", "update skills", "list skills", "deduplicate skills", "why are two skills shown", "choose the canonical…
agents-consilium
Run external coding agents (Codex, Claude Code, OpenCode, native Grok Build, Gemini) as independent reviewers, stateful repository researchers, or single-agent implementers. Use for multi-model opinions and code review, steerable Grok research, full-access delegation, long-running work, or reattaching to delegated…
plugins-management
Create, publish, delete, and submit plugins for coding agents (Claude Code, OpenCode). Use when user wants to (1) create a new plugin with proper structure, (2) create or configure a plugin marketplace, (3) publish plugins to GitHub/GitLab/npm, (4) delete/uninstall plugins, (5) validate plugin structure, or (6)…