agentleFS
richardochristjiarichardochristjia/skills/simple-loop/SKILL.md

simple-loop

Skill2 starsChanged 7 days agoMITView on GitHub

Execute a phased plan from `.plans/{task}/` task by task, using `check` output to steer edits, with tests and a commit per phase. Use for everyday multi-phase work, including large refactors where the build breaks between tasks.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Sync before the next phase: Run sync at the end of every committed phase.

    line 20
  2. Very specific:

    Broken builds: if check fails, fix and re-run.

    line 42
  3. Very specific:

    Verify: Run the full test suite and fix failures before proceeding.

    line 46
  4. Distinctive:

    Follow Finishing in the rules file.

    line 54

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Simple Task Loop

A disciplined workflow for implementing multi-phase coding tasks. tasks.md tracks progress in real time. The compiler is your guide: run check often and let its errors show what still needs updating.

Arguments: $ARGUMENTS — the plan (a .plans/<task>/ path or slug). Always run the whole plan.

Picked by pick-tier when the tier is L, with no sensitive path and 3 phases or fewer (or no phase count).

Read task-loop-rules.md in this skill's folder first. It holds the project commands, constraints, concepts, task-list discipline, and finishing steps all three task loops share. This file adds only what is specific to this loop.

Constraints (on top of the shared ones)

  • Sync before the next phase. Run sync at the end of every committed phase.

The Loop

Repeat until every task is complete. Work per phase, top to bottom.

  1. Check status. Read tasks.md. Every task [x] → go to When you are done. Otherwise start at the next task.
  2. Gather what the current phase needs: the spec sections it implements and the code it touches.
  3. Implement, one task at a time:

    a. Restate the current task in one sentence.

    b. Do the work. Run check after each logical group of changes — a single task, a phase, or several phases, depending on the work. Use its output to steer: rename something and the errors list every call site still to update. You only see that guidance by actually running it.

    c. Tick it in tasks.md.

    d. Pick the next task under the current phase header and repeat from (a). When the phase has no - [ ] left, go to 3.5.

    Broken builds: if check fails, fix and re-run. Large refactors can leave the build red until a later task lands; that is expected. Once the code should build, it must.

3.5. Audit. Re-read tasks.md. Any task in this phase not [x] means you drifted: return to step 3 with it. The list must be clean before you test or commit.

  1. Verify. Run the full test suite and fix failures before proceeding. If a phase must end with a broken build (a refactor spanning phases), first try reordering tasks so every phase ends green; accept a red phase boundary only when no order allows it.
  2. Commit and sync. On a green build: commit with a Conventional Commit message, <type>(<scope>): <summary>, one per phase, with the phase named in the summary or body, then sync (resolve conflicts, re-test, commit the merge). On a red build: skip both and commit at the next phase that builds.
  3. Go to step 1.

When you are done

Follow Finishing in the rules file.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.