execute-plan SKILL.md skillA

execute-plan from melconcoast/code-idea is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add melconcoast/code-idea/execute-plan@v5.1.0

Pins v5.1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
melconcoast/code-idea
Path
.agents/skills/execute-plan/SKILL.md
Versions recorded
5
Latest version
v5.1.0, committed Nov 2, 2026
First version recorded
Sep 3, 2026
Size
10,952 bytes
Repository stars
4
License
MIT

Use this skill when the user says things like "execute the plan", "build task 2.1", "start phase 2", "continue building this module", "implement the next task", "work through the plan", or is ready to write code against a plan file that already exists. Not for creating a project's agent docs or its roadmap — use scaffold. Not for cutting a module into phases or re-planning one — use plan-module. Not for designing screens or making mockups — use design-ui. Builds a module from the plan file…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# execute-plan

Builds a module from its plan file one task at a time — real code, real tests, actually run — and keeps the plan file and the roadmap true as it goes.

## When this runs
- A `docs/guides/feature_<module>_plan.md` exists and the user is ready to build it
- Work resumes on a plan already partly closed — pick up at the first open task, never restart
- Never as a project's first step. No plan file means there is nothing to execute: hand off to `plan-module`, or to `scaffold` if there's no `docs/development-roadmap.md` either

## Core philosophy — hold these through every loop
- **One task, then verify, then write.** Implement exactly one development task and the scenarios beneath it, get them green, update the plan file, and only then look at the next task. Batching a phase is how a plan file stops matching the code it claims to describe.
- **`[x]` means verified, not written.** A task whose code exists but whose scenarios never ran is still `[ ]`. Never close an item on inspection, on intent, or on a type-check alone — something has to have actually run.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add melconcoast/code-idea/execute-plan@sha256:4d0923288a5c9560

The line at the top of this page pins the label v5.1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_dtifnbiqq57n44by.svg)](https://markdownregistry.com/a/art_dtifnbiqq57n44by)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Sep 3, 2026 and Nov 2, 2026, about one every 15 days.

versioncommittedcommitsizeaudit
v5.1.0 latest2026-11-02 3d78889 10,952 BA view · diff
v5.0.02026-10-08 1497fd6 10,952 BA view · diff
v5.0.02026-10-08 f9486dc 10,691 BA view · diff
v4.2.12026-09-03 d269a0c 9,576 BA view · diff
v4.2.02026-09-03 92a4a5b 9,576 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (10952 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

melconcoast/code-idea · 4 stars · license MIT · pushed 2026-11-02 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_dtifnbiqq57n44by
GET https://markdownregistry.com/api/v1/resolve?ref=melconcoast/code-idea/execute-plan
GET https://markdownregistry.com/api/v1/blob/4d0923288a5c956051a6df3a34b6eb81fc5a761a9ab07d1dea4ed03be7f22d34

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from melconcoast/code-idea

design-brand SKILL.md skill
melconcoast/code-idea · .agents/skills/design-brand/SKILL.md · Use this skill when the user says things like "create a brand", "build our brand", "brand book", "import my brand…
v5.1.0 · audit A · 4 stars
design-ui SKILL.md skill
melconcoast/code-idea · .agents/skills/design-ui/SKILL.md · Use this skill when the user says things like "design the UI", "make mockups", "mock up the screens", "import my…
v5.1.0 · audit A · 4 stars
plan-module SKILL.md skill
melconcoast/code-idea · .agents/skills/plan-module/SKILL.md · Use this skill when the user says things like "plan the next module", "plan module 3", "break this module into phases"…
v5.1.0 · audit A · 4 stars
scaffold SKILL.md skill
melconcoast/code-idea · .agents/skills/scaffold/SKILL.md · Use this skill whenever the user wants to turn a plan/idea into files for Claude Code or another coding agent, says…
v5.1.0 · audit A · 4 stars
test-and-verify SKILL.md skill
melconcoast/code-idea · .agents/skills/test-and-verify/SKILL.md · Use this skill whenever tests are to be run or a failure chased down — "run the tests", "run the test suite", "verify…
v5.1.0 · audit A · 4 stars
AGENTS.md AGENTS.md file
melconcoast/code-idea · AGENTS.md
git:20261102.3d78889 · audit A · 4 stars
CLAUDE.md CLAUDE.md file
melconcoast/code-idea · CLAUDE.md
git:20260812.c6fc180 · audit B · 4 stars
CLAUDE.md@examples/fixtures/pickup-queue CLAUDE.md file
melconcoast/code-idea · examples/fixtures/pickup-queue/CLAUDE.md
git:20260903.482a115 · audit A · 4 stars
AGENTS.md@examples/sample-output AGENTS.md file
melconcoast/code-idea · examples/sample-output/AGENTS.md
git:20260823.332af3b · audit A · 4 stars
CLAUDE.md@examples/sample-output CLAUDE.md file
melconcoast/code-idea · examples/sample-output/CLAUDE.md
git:20260813.77236e2 · audit A · 4 stars

Every file in melconcoast/code-idea

Other files named execute-plan

execute-plan SKILL.md skill
tailcallhq/forgecode · crates/forge_repo/src/skills/execute-plan/SKILL.md · Execute structured task plans with status tracking. Use when the user provides a plan file path in the format…
git:20251124.2b8f212 · audit A · 7,636 stars
execute-plan SKILL.md skill
ovich/swarmstorm · skills/execute/execute-plan/SKILL.md · Use when carrying out an implementation plan the person has already approved, whether starting it or resuming it in a…
git:20261024.148caad · audit A · 13 stars
execute-plan SKILL.md skill
cliver-project/cliver · packages/cliver/src/cliver/skills/builtin/execute-plan/SKILL.md · Systematically execute a written implementation plan task by task with verification. Use after write-plan or when you…
git:20261025.d71167b · audit A · 8 stars
execute-plan SKILL.md skill
dbc-oduffy/coordinator-claude · skills/execute-plan/SKILL.md · Execute a PM-approved plan via per-chunk executor waves.
git:20261029.ed49b76 · audit B · 6 stars
execute-plan SKILL.md skill
teambrilliant/dev-skills · skills/execute-plan/SKILL.md · Execute an approved plan from thoughts/plans/ to completion — every phase, every check, every acceptance criterion —…
git:20261026.069feb8 · audit A · 5 stars

Browse by kind, by grade A, or by owner.