Home / teambrilliant / dev-skills · skills/execute-plan/SKILL.md · GitHub

execute-plan skillA

execute-plan is agent-read markdown (skill) from teambrilliant/dev-skills: Execute an approved plan from thoughts/plans/ to completion — every phase, every check, every acceptance criterion — and stop only when DONE or BLOCKED. Use when someone says "execute the plan", "implement the plan", "build it" after a plan was approved, "start building", or points at a file in thoughts/plans/. Medium/large work without a plan → /dev-skills:write-plan first..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified before it reaches your agent: the main file against the SHA-256 recorded here, the others against the git hashes of its source commit. The deterministic audit below grades the latest version, and the same checks always give the same file the same grade.

What the file says

# Execute Plan

Carry an approved plan through to working, verified code. The plan is a contract: you either satisfy it or show exactly why it can't be satisfied.

## Input

A plan in `thoughts/plans/` (from `/dev-skills:write-plan`). No plan and the work is medium/large → write one first. No plan and the work is small and clear → state the acceptance criteria in one line each, then run under the same contract.

## The Contract

Approval of the plan is the only gate. From then on you own delivering it, and a run ends in exactly one of two states:

**DONE** — every phase implemented; every phase check green; full test suite, typecheck and lint with no new failures against the baseline you recorded at the start; every acceptance criterion verified with cited evidence. For UI criteria, that means you ran `/dev-skills:qa-test` yourself and it passed.

**BLOCKED** — the contract can't be satisfied without something only the user can provide:
- a permission, credential, or access you don't have (and the plan's pre-flight blockers didn't cover)
- a harness that can't be made runnable by you — a check needs a human step with no bypass
…

Read the whole file at its exact version.

How to install

Latest version
mdr add teambrilliant/dev-skills/execute-plan@git:20260927.b9558d0
Exact content
mdr add teambrilliant/dev-skills/execute-plan@sha256:8464b808186ebc9c

Pin to a label to follow the author's releases, or to a sha256 for exact bytes. Either way the resolved hash is written to mdr.lock, and mdr install fetches those bytes again and checks them, so it installs them exactly or fails.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_k6vhpkvybltthmqd.svg)](https://markdownregistry.com/a/art_k6vhpkvybltthmqd)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260927.b9558d0 latest2026-09-27 b9558d0 7,394 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (7394 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

teambrilliant/dev-skills · 6 stars · license none · pushed 2026-09-27 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_k6vhpkvybltthmqd
GET https://markdownregistry.com/api/v1/resolve?ref=teambrilliant/dev-skills/execute-plan
GET https://markdownregistry.com/api/v1/blob/8464b808186ebc9c8cb4932214d519d80c439969bbe8a12dd8b09cee474f5ff2

Your agent 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.

More from teambrilliant/dev-skills

CLAUDE.md claude
teambrilliant/dev-skills · CLAUDE.md
git:20260927.b9558d0 · audit A · 6 stars
explain skill
teambrilliant/dev-skills · skills/explain/SKILL.md · Explain a plan, a shape, a shipped change, code, or the last message so it's impossible to misunderstand — an ASCII…
git:20260927.b9558d0 · audit A · 6 stars
product-discovery skill
teambrilliant/dev-skills · skills/product-discovery/SKILL.md · Validate whether a product idea will actually work before committing engineering — find what you don't know, design the…
git:20260927.b9558d0 · audit A · 6 stars
product-primitives skill
teambrilliant/dev-skills · skills/product-primitives/SKILL.md · Break down complex products, features, or systems into fundamental primitives and building blocks from a software…
git:20260507.c5d07e6 · audit A · 6 stars
product-thinker skill
teambrilliant/dev-skills · skills/product-thinker/SKILL.md · Use for product decisions, user behavior analysis, and UX evaluation. Trigger when the user wants to: evaluate whether…
git:20260927.b9558d0 · audit A · 6 stars
qa-test skill
teambrilliant/dev-skills · skills/qa-test/SKILL.md · Browser-based QA verification after any implementation. Use when someone says "QA this", "test this in browser"…
git:20260927.b9558d0 · audit A · 6 stars
shaping-work skill
teambrilliant/dev-skills · skills/shaping-work/SKILL.md · Shape rough ideas into clear, actionable work definitions. Use this skill whenever someone has an unstructured idea…
git:20260927.b9558d0 · audit A · 6 stars
strategic-thinker skill
teambrilliant/dev-skills · skills/strategic-thinker/SKILL.md · Use for cross-domain strategic reasoning, approach selection, and systems-level analysis. Trigger when the user wants…
git:20260927.b9558d0 · audit A · 6 stars
working-backwards skill
teambrilliant/dev-skills · skills/working-backwards/SKILL.md · Write an Amazon-style PR-FAQ (mock press release + FAQ) to pressure-test a product idea customer-first and kill weak…
git:20260927.b9558d0 · audit A · 6 stars
write-plan skill
teambrilliant/dev-skills · skills/write-plan/SKILL.md · Write a technical implementation plan to thoughts/plans/ before coding starts (separate from the harness's plan mode)…
git:20260927.b9558d0 · audit A · 6 stars

Every file in teambrilliant/dev-skills

Other files named execute-plan

execute-plan 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 · 7,637 stars
execute-plan skill
dbc-oduffy/coordinator-claude · skills/execute-plan/SKILL.md · Executes a PM-approved plan via dispatched per-chunk executor waves.
git:20260925.9b3c461 · audit B · 5 stars

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