redo
Skill1 starsChanged 4 months agoMITView on GitHub
Re-run the last routed task one model tier up (haiku → sonnet → opus → fable). User-invoked escalation when the previous result missed. Pass --dry-run to preview without running.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- udecode/better-convextheir own version, first seen Nov 9, 2026
- udecode/platetheir own version, first seen Oct 17, 2026
- udecode/dotaitheir own version, first seen Oct 13, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- udecode/plate★ 17ksame name
- udecode/dotai★ 1.2ksame name
- udecode/better-convex★ 452same 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. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
2
Distinctive
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 15
If the context above says "last-task: none", tell the user there is nothing to redo and stop.
- Very specific: line 17
If the context above contains a dry-run: line, relay the three context lines to the user verbatim in one fenced code block and STOP.
- Distinctive: line 30
Do not modify, shrink, or expand the task.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Redo — escalate the last routed task
Last delegation (from .router/log.jsonl):
!node "${CLAUDE_PLUGIN_ROOT}/scripts/last-task.js" $ARGUMENTS
Re-run that task one tier up. Follow these steps exactly:
- If the context above says "last-task: none", tell the user there is nothing to redo and stop.
- If the context above contains a
dry-run:line, relay the three context lines to the user verbatim in one fenced code block and STOP. Do not delegate, do not use the Agent tool, do not modify any file — a dry run must leave .router/log.jsonl byte-identical. - The target is the
next:line above. Exactly one tier up - never skip tiers, never stay at the same tier (unless already at fable). - The router announces the delegation automatically. Give the Agent call a plain-ASCII description ≤32 chars.
- Delegate the SAME task to the target agent. If the
next:line says(model: fable), pass model "fable" in the Agent tool call - the per-invocation model outranks the agent's default. Use the full task prompt from your conversation context if you delegated it this session; otherwise reconstruct it faithfully from thelast-task:line above. Do not modify, shrink, or expand the task. - Relay the new result to the user.
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.