routing-policy
Skill1 starsChanged 4 months agoMITView on GitHub
Model-routing rubric. Use when deciding which worker agent (haiku-worker, sonnet-worker, opus-worker, fable-architect) should handle a task, whether to delegate at all, or which model tier a prompt deserves.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- sergeeey/Claude-cod-top-2026their own version, first seen May 13, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- sergeeey/Claude-cod-top-2026★ 9same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Use this rubric to choose the cheapest worker capable of completing the task.
- Very specific: line 27
When in doubt between two tiers, pick the lower and note that escalation is one /router:redo away, unless the directive's mode line, when …
- Distinctive: line 35
Do not delegate interactive or back-and-forth work, ambiguous specs needing user questions, conversational answers, or tasks taking under …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Routing policy
Use this rubric to choose the cheapest worker capable of completing the task.
| Task type | Trivial | Standard | Complex |
| Mechanical edit | haiku-worker | haiku-worker | sonnet-worker |
| Doc/comment change | haiku-worker | haiku-worker | sonnet-worker |
| Single-file bugfix | haiku-worker | sonnet-worker | opus-worker |
| Feature, few files | sonnet-worker | sonnet-worker | opus-worker |
| Multi-file refactor | sonnet-worker | opus-worker | opus-worker |
| Debugging unknown cause | sonnet-worker | opus-worker | opus-worker |
| Architecture/design | fable-architect | fable-architect | fable-architect |
| Planning/review | sonnet-worker | sonnet-worker | fable-architect |
Delegation rules
- The cheapest capable tier wins.
- When in doubt between two tiers, pick the lower and note that escalation
is one
/router:redoaway, unless the directive's mode line, when present, overrides the pick-the-lower default. - The router hook prints the one-liner below. Give every Agent call a plain-ASCII description ≤32 chars. Never delegate silently.
When NOT to delegate
Do not delegate interactive or back-and-forth work, ambiguous specs needing user questions, conversational answers, or tasks taking under about 30 seconds.
One-liner contract
→ <agent> · <task summary ≤32 chars> · /router:redo to escalate
<agent> is the basename without the router: prefix.
Exactly one glyph (→); the whole line must fit in 80 columns.
The hook prints this line for every delegation, including auto-escalations. The model's duty is a plain-ASCII description ≤32 chars on every Agent call.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.