icebox
Skill3 starsChanged 36 days agoMITView on GitHub
Icebox a raised-but-undecided concern instead of forcing a plan-or-dismiss call: record it with no verdict so the context survives. Use when a review, PR, audit, or eval surfaces something real-maybe that should not be scheduled or closed yet, or when the user says to icebox or park an item.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- nrjdalal/zerostarteredited, first seen Oct 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- nrjdalal/zerostarter★ 6598% same
Wrote their own version · 0
None found.
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.
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- add-packageSkill
- agent-browserSkill
- api-endpointSkill
- auditSkill
- codebase-mapSkill
- db-migrationSkill
- designSkill
- devSkill
- docker-testSkill
- doc-syncSkill
- fontsSkill
- gh-commitSkill
- ignore-syncSkill
- portlessSkill
- releaseSkill
- runtime-apisSkill
- shadcn-syncSkill
- shipSkill
- skills-managerSkill
- ui-verifySkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 26
Write the concern to .github/notes/plans/<slug>.md, or append a section to a fitting file: state the concern, its context, and the open …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
[!CAUTION] Synced from https://github.com/nrjdalal/zerostarter. Customize this skill or remove this note to stop syncing.
Icebox
Some concerns are real yet not decidable right now. Forcing one into a plan overstates it; closing it loses the context. Ice is the third option: park the concern verbatim, with no verdict, until someone can rule on it. It sits between the plans backlog and a closed issue. The full definition and the standing index live in .github/notes/plans/README.md.
What belongs on ice
Ice is only for the genuinely undecided, all three at once:
- Raised by a review note, a PR follow-up, or an audit or eval finding.
- Not schedulable into the plans backlog, because no next action is agreed.
- Not resolvable as fix-it or not-a-problem with any confidence.
A known next action belongs in the plans backlog; a confident verdict gets shipped or closed. Everything else waits on ice until it thaws into one of those.
Park it
- Write the concern to
.github/notes/plans/<slug>.md, or append a section to a fitting file: state the concern, its context, and the open question, with no plan and no verdict. Done when a reader grasps what is unresolved and finds no recommendation. - Link it under
## Iceboxin.github/notes/plans/README.md. Done when the index points at the file. - Mirror the one-liner and the
plans/<slug>.mdpath as an unchecked box on the standing Icebox issue (#707). Done whengh issue view 707shows it.
Thaw
An item leaves ice only by being decided. When that happens, check its box in #707, record the outcome (shipped, dismissed, or moved to the backlog), and graduate its write-up to the plans backlog or delete it.
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.

