Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 

Repository files navigation

Task Loop

A standing methodology for any non-trivial task: instead of executing ad-hoc and handing back the first draft, structure the work as a self-extending nine-step loop that keeps going until the result is actually good.

The loop, one iteration:

  1. Research — internal (read the code, run --help, fetch docs) + external (state of the art)
  2. Plan — write it down as an artifact, don't interleave with execution
  3. Execute — implement the plan
  4. Operational audit — are we building what was asked? Is it state-of-the-art yet?
  5. Technical audit — correctness, edge cases, security, performance, tests
  6. Integrate findings — append a discrete fix task for every issue surfaced
  7. Test / secondary audit — verify against real-shaped input
  8. Analyze results — be honest; "tests passed" ≠ "perfect"
  9. Decide — loop again (hard cap 3×), advance to the next section, or zoom out

Cross-loop state lives in a per-scope implementation plan (plan-{scope}-{date}.md), never in a shared roadmap.md/status.md — those mix scopes and cause collisions.

Two variants

Variant For Tracks the loop with
task-loop/ Claude / Claude Code TodoWrite
task-loop-codex/ OpenAI Codex update_plan

The two are identical in logic and content. The only difference is the plan-tracking tool each agent uses (and the name/title).

Install

Drop the relevant folder into your agent's skills directory:

  • Claude Code: copy task-loop/ to ~/.claude/skills/task-loop/
  • Codex: copy task-loop-codex/ into your Codex skills/agents directory

About

Task Loop — a self-extending nine-step loop methodology for substantive agent work. Claude (TodoWrite) + Codex (update_plan) variants.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors