agentleFS
Sign inStart free
aicodekingaicodeking/deepseek-stack/skills/ds-plan-loop/SKILL.md

ds-plan-loop

Skill80 starsChanged 15 days agoMITView on GitHub

Write a numbered plan with an acceptance check for each step, critique it once in a fresh pass, revise it, then execute one step at a time. Use when a task touches more than one file, has unclear scope, or failed before because steps were missed. Invoke as /ds-plan-loop.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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
  1. Very specific:

    Write a numbered plan. Each step gets one action and one acceptance check that a command or a direct observation can confirm, for example …

    line 13
  2. Distinctive:

    Write the plan to a file (PLAN.md, or the PROGRESS.md from ds-context-reset) so later steps and fresh sessions can read it.

    line 14
  3. Distinctive:

    If a step shows that the plan is wrong, stop and revise the remaining steps before continuing.

    line 22
  4. Distinctive:

    Every step is marked done and its check passed, and the original goal holds when you check it end to end.

    line 26
  5. Distinctive:

    No step without a check. "Looks right" is not a check.

    line 32
  6. Distinctive:

    Do one step per diff. Do not batch steps to save time.

    line 33
  7. Distinctive:

    Do not add steps that the goal does not need.

    line 34
  8. Distinctive:

    Keep the plan short: about 3-10 steps.

    line 35

≈ “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

ds-plan-loop

Plan before coding, check the plan once, then build the task one verified step at a time.

Steps

  1. Restate the goal in one sentence. List the files and commands you expect to touch. Read those files before you plan. Do not plan from memory.
  2. Write a numbered plan. Each step gets one action and one acceptance check that a command or a direct observation can confirm, for example "npm test -- auth passes" or "GET /health returns 200". Keep each step small enough to verify in a single diff.
  3. Write the plan to a file (PLAN.md, or the PROGRESS.md from ds-context-reset) so later steps and fresh sessions can read it.
  4. Critique the plan in a fresh pass. Reread only the goal and the plan, as a reviewer who did not write it. If you can, run the critique in a subagent or new session. Answer three questions:
    • Which step is missing (setup, migration, config, tests, cleanup)?
    • Which assumption has not been checked against the code or docs?
    • Is there a simpler path that reaches the same goal with fewer steps?
  5. Revise the plan. Check each risky assumption now by reading code or running a command. Do not carry it forward as a guess.
  6. Execute step 1 only. Run its acceptance check and read the real output. Use ds-verify-loop when the check fails.
  7. Mark the step done in the plan file, along with the evidence (command and result). Then move to the next step.
  8. If a step shows that the plan is wrong, stop and revise the remaining steps before continuing. Do not improvise around it.

Stop when

  • Every step is marked done and its check passed, and the original goal holds when you check it end to end.
  • You have done 2 critique rounds. A third round almost never finds anything new, so execute.
  • A step fails its check twice in a row. Switch to ds-unstick.

Rules

  • No step without a check. "Looks right" is not a check.
  • Do one step per diff. Do not batch steps to save time.
  • Do not add steps that the goal does not need.
  • Keep the plan short: about 3-10 steps. Split bigger work into separate plans.

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.

Check your setup, free