loop-plan
Skill8 starsChanged 4 months agoMITView on GitHub
The planning session. Turns a goal into an ordered list of thin complete slices, decides which role and model runs each following session, and writes it all to the plan file. Use at the start of an epic, before any code.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- kaiitunnz/claude-skillstheir own version, first seen Sep 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- kaiitunnz/claude-skills★ 1same 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.
In this repository6 other files it gives its agents.
- loop-closeSkill
- loop-councilSkill
- loop-doctorSkill
- loop-setupSkill
- loopSkill
- loop-verifySkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Before planning *how*, state what this is for and what it has to actually achieve.
- Distinctive: line 16
If that is not clear, clarify it now — with the owner if it is a business decision, by reading the code if it is a technical one.
- Distinctive: line 27
If the epic has more than one plausible shape, dispatch two or three planners with different framings in a single message (for example: …
≈ “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
Plan the epic
This is the session that decides everything the cheaper sessions will do. It is worth spending real thinking here — but the thinking must land on disk, because a plan that only exists in this conversation dies with it.
1 · Get the goal straight first
Before planning how, state what this is for and what it has to actually achieve. If that is not clear, clarify it now — with the owner if it is a business decision, by reading the code if it is a technical one. A plan aimed at a fuzzy goal produces work that is complete and useless.
2 · Dispatch the expensive thinking
Send the planning work to the loop-planner agent (its model and effort are
fixed in its own definition, so the quality of the plan does not depend on how this
session happened to be launched). Give it: the goal, the relevant paths, and
.loop/VERIFY.md.
If the epic has more than one plausible shape, dispatch two or three planners with different framings in a single message (for example: smallest-shippable-first, risk-first, user-first), then take the best and graft what is worth keeping from the others. Say which framing won and why.
For anything touching money, permissions, auth, or schema, run loop-council on the
design before it becomes a slice.
3 · Write the plan to .loop/STATE.md
# Epic: <name> Goal: <what it must actually achieve>
[ ] 1. <slice>
non-negotiables: <what must be true to count as done>
verify: BUILD + OBSERVE + DATA
run: ./loop build # session role that should execute it
[ ] 2. <slice>
...
Deliberately out of scope: <what and why>Order the slices so each one is safe to stop after. Depth before breadth: one epic at a time, and nothing new opens until what is open is closed.
4 · Assign a role to each following session
Each slice carries the command that runs it. The roles exist because the work is not all the same shape:
| Role | Command | What it is for |
| plan | ./loop plan "<goal>" | this session — split, decide, do not code |
| build | ./loop build | implement the next slice completely |
| verify | ./loop verify | run the contract and judge honestly |
| close | ./loop close | adversarial audit, ledger, handoff |
Be honest about the limit: a session cannot change its own model once it is running, and it cannot even read which model it is on. So a plan does not switch the next session — it hands over the exact command to launch it, and the expensive roles carry their model in their own agent definition so that quality survives a sloppy launch. If unattended runs are wanted, the same command goes in a scheduler.
5 · Close the planning session
Print the slice list, the first command to run, and what you left out. Do not start building — a planning session that starts coding stops planning.
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.