later-list
Skill0 starsChanged 19 days agoMITView on GitHub
Put a tangent on the later list (one line in LATER.md) and go back to the current task, then sort the list at a natural break (do now, schedule, drop). Applies to the user's ideas and to side issues the agent finds while working, such as an unrelated bug, refactor or doc gap. Use when the user says 'park this', 'note that for later', 'side quest', 'remind me', or when a new idea or unrelated fix shows up mid-task. Not for blockers of the current task (handle those now).
In this repository57 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/comments.mdcCursor rule
- .cursor/rules/commit-messages.mdcCursor rule
- .cursor/rules/git-workflow.mdcCursor rule
- .cursor/rules/manage-stack.mdcCursor rule
- .cursor/rules/no-worktrees.mdcCursor rule
- manage-stackSkill
- convert-as-skillSkill
- create-agentSkill
- create-agents-mdSkill
- create-commandSkill
- create-hookSkill
- create-ruleSkill
- create-skillSkill
- retrospectiveSkill
- super-architectureSkill
- super-cachingSkill
- super-elixirSkill
- super-nodejsSkill
- super-protobufSkill
- super-tech-blueprintSkill
- atomic-semantic-commitSkill
- code-reviewSkill
- create-bruno-collectionSkill
- create-documentationSkill
- create-ticketsSkill
- ready-specSkill
- write-adrSkill
- write-changelogSkill
- write-mr-descriptionSkill
- write-planSkill
- write-postmortemSkill
- write-runbookSkill
- noslopSkill
- output-saversSkill
- safe-refactorSkill
- tddSkill
- verifySkill
- get-movingSkill
- standupSkill
- challenge-meSkill
- codebase-learnerSkill
- researchSkill
- second-opinionSkill
- traceSkill
- color-kitSkill
- design-system-kitSkill
- diagramSkill
- infographicSkill
- product-polish-workflowSkill
- prototype-wireframeSkill
- ui-ux-kitSkill
- evidenceSkill
- find-skillsSkill
- handoffSkill
- rumblingSkill
- use-levistackSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 30
Check it can wait: If the current task cannot finish without it, it is a blocker.
- Distinctive: line 35
Keep it to one line. A long entry is a new task in disguise.
- Distinctive: line 53
Do not ask the user before adding a line.
- Very specific: line 54
Do not commit LATER.md unless the user wants it tracked.
≈ “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
Later list
Tangents are fine. Chasing them mid-task is how the first task never gets finished.
Steps
- Name the current task in one line, so you know what you return to.
- Check it can wait. If the current task cannot finish without it, it is a blocker. Say so and handle it now.
- Append one line to
LATER.mdat the repo root (create it if missing; outside a repo, use the cwd):
Keep it to one line. A long entry is a new task in disguise.- [ ] 2026-10-25 · <idea or issue> · <why it might matter> · <file or link, if any> - Do not research, fix or start it. Capturing it is the whole job. An agent that found an unrelated bug lists it and does not fix it in this diff.
- Go back to the step you were on and say which step that is.
Sort at a break
At a natural break (end of a round, before a handoff, end of the day), read LATER.md and decide for each open line:
| Decision | Do |
| Do now | It is small and related. Do it next, then tick it [x] |
| Schedule | Move it to a ticket, plan or handoff note, then tick it with a pointer |
| Drop | Delete the line |
Ticked lines older than a week can go.
Pitfalls
- Do not ask the user before adding a line. Add it, tell them in one line, and continue.
- Do not commit
LATER.mdunless the user wants it tracked. Mention it once if it is untracked.
Related skills
get-moving: pick the next step after you list a tangent.write-plan: an item on the list grew into real work.handoff: carry open items into the next session.
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.