agentleFS
monaccodemonaccode/astromesh-sdd/skills/sdd-plan/SKILL.md

sdd-plan

Skill0 starsChanged 29 days agoApache-2.0View on GitHub

Use when a feature's spec.md is approved and there is no plan.md yet, or the spec changed after planning. Writes plan.md - architecture decisions, files to touch, risks and test strategy - where every step cites the requirements it serves.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before anything else, read these if they exist.

    line 14
  2. Very specific:

    Write every artifact in language.

    line 25
  3. Very specific:

    Read spec.md (and <specs_dir>/constitution.md if present).

    line 30
  4. Very specific:

    If an earlier custom phase left its own artifact in the feature folder (for example adr.md), read it too: the plan must follow it.

    line 34
  5. Very specific:

    Write plan.md from the template:

    line 45
  6. Distinctive:

    Update only the affected steps, decisions and coverage rows.

    line 66
  7. Very specific:

    If plan is in gates: show the user the artifact path and a 3–5 line summary, list any [NEEDS CLARIFICATION] items, and stop.

    line 71

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

SDD — Plan

The plan turns the approved spec into a technical approach: what changes where, which decisions were made and what was rejected, how each requirement will be proven. It is the first phase allowed to talk about code.

Step 0 — Load project settings

Before anything else, read these if they exist. Missing files are normal; use the defaults.

  1. .sdd/config.yaml in the project, else ~/.sdd/config.yaml. Defaults: specs_dir: specs, language: en, ids: {requirement: REQ, task: T}, gates: [specify, plan, tasks], verify_command: "", phases: [constitution, specify, plan, tasks, implement, verify].
  2. Template: .sdd/templates/plan.md, else ~/.sdd/templates/plan.md, else templates/plan.md next to this file.
  3. Extra rules: .sdd/rules/all.md and .sdd/rules/plan.md (project, then global). They add to this skill; when they conflict with it, they win.

Write every artifact in language. Use the configured ID prefixes everywhere this skill says REQ or T.

Step 1 — Preconditions

Read spec.md (and <specs_dir>/constitution.md if present). If the spec still has [NEEDS CLARIFICATION] items, resolve them with the user first — through sdd-specify's "Changing a spec" rules — before planning. Planning around an open question bakes in a guess.

If an earlier custom phase left its own artifact in the feature folder (for example adr.md), read it too: the plan must follow it.

Step 2 — Understand the code it touches

Trace the real flow end to end for the behavior the spec changes: entry point, the functions and modules on the path, the data they share, the tests that cover them today. Reuse what exists before proposing anything new.

Step 3 — Write plan.md

Write plan.md from the template:

  • Approach — 2–4 sentences a newcomer can follow.
  • Decisions — each with the alternative you rejected and why. A decision with no rejected alternative is not a decision; leave it out.
  • File map — every file to create or modify, with its one responsibility.
  • Steps — ordered; each cites at least one REQ-n.
  • Risks — each with how you would notice it going wrong.
  • Test strategy — for every REQ, how it will be verified (test type and what it asserts).
  • Respect every principle in the constitution; if the plan must break one, say so explicitly and why, so the user can decide.

Step 4 — Coverage check

Fill the Coverage table: every requirement in the spec and the steps that cite it. A requirement with no step is a blocker — add the step or go back to the spec. Removed requirements (~~REQ-n~~) are skipped.

When the spec changes after planning

Update only the affected steps, decisions and coverage rows; keep the rest. Note the change at the end of the Approach section with the date.

Gate

If plan is in gates: show the user the artifact path and a 3–5 line summary, list any [NEEDS CLARIFICATION] items, and stop. Do not start the next phase until the user approves. When they approve, set the artifact's status line to **Status:** approved · **Date:** YYYY-MM-DD and save the file — approval has to live in the file, so a later session or another agent can see it. If plan is not in gates, set the status to approved yourself, say which phase runs next and continue.

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.