/implement-from-plan
Implement an approved plan doc step-by-step in application or systems codebases, including Node/TS, Python, and C/C++ repos (build/lint/test per step, atomic commits, progress log hygiene). Use when you have a plan/*.md and want to execute it.
$ npx -y skills add besimple-oss/broccoli --skill implement-from-plan --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/implement-from-plan
Context preview
The summary Claude sees to decide when to auto-load this skill.
Implement an approved plan doc step-by-step in application or systems codebases, including Node/TS, Python, and C/C++ repos (build/lint/test per step, atomic commits, progress log hygiene). Use when you have a plan/*.md and want to execute it.
SKILL.md
implement-from-plan.SKILL.mdname: implement-from-plan
description: "Implement an approved plan doc step-by-step in application or systems codebases, including Node/TS, Python, and C/C++ repos (build/lint/test per step, atomic commits, progress log hygiene). Use when you have a plan/*.md and want to execute it."
Implement From Plan (step-by-step)
Input: a plan doc path (for example: `plan/my-feature.md`).
Preconditions (stop if missing)
1. Confirm you are in the intended repo: `git rev-parse --show-toplevel` 2. Confirm the plan doc exists: `test -f <plan-doc-path>` 3. Confirm the working tree is clean: `git status --porcelain` is empty 4. Ensure `codex-progress.log` is gitignored and not tracked:
- Add `codex-progress.log` to `.gitignore` if missing.
- If it is tracked: `git rm --cached codex-progress.log` (keep the file locally).
Workflow
1. Record a base commit for later review: `BASE_SHA=$(git rev-parse HEAD)` 2. When running this skill with Codex, use model `gpt-5.4` unless the caller explicitly overrides the model. 3. Open `references/prompts/step-auto-mixed.md` and follow it using the plan doc path.
- Important: it includes a one-time tooling discovery + dependency install + "Tooling config" phase; do that once and reuse it for every step.
- For C/C++ repositories, extend the prompt's tooling discovery to identify the repo-native build/test/lint path before Step 1. Check for `CMakeLists.txt`, `compile_commands.json`, `meson.build`, `BUILD`/`WORKSPACE`, `Makefile`, and repo docs. Reuse the canonical configure/build/test/lint commands for each later step instead of rediscovering them.
Read more
name: implement-from-plan description: "Implement an approved plan doc step-by-step in application or systems codebases, including Node/TS, Python, and C/C++ repos (build/lint/test per step, atomic commits, progress log hygiene). Use when you have a plan/*.md and want to execute it."
Implement From Plan (step-by-step)
Input: a plan doc path (for example: `plan/my-feature.md`).
Preconditions (stop if missing)
1. Confirm you are in the intended repo: `git rev-parse --show-toplevel` 2. Confirm the plan doc exists: `test -f <plan-doc-path>` 3. Confirm the working tree is clean: `git status --porcelain` is empty 4. Ensure `codex-progress.log` is gitignored and not tracked:
- Add `codex-progress.log` to `.gitignore` if missing.
- If it is tracked: `git rm --cached codex-progress.log` (keep the file locally).
Workflow
1. Record a base commit for later review: `BASE_SHA=$(git rev-parse HEAD)` 2. When running this skill with Codex, use model `gpt-5.4` unless the caller explicitly overrides the model. 3. Open `references/prompts/step-auto-mixed.md` and follow it using the plan doc path.
- Important: it includes a one-time tooling discovery + dependency install + "Tooling config" phase; do that once and reuse it for every step.
- For C/C++ repositories, extend the prompt's tooling discovery to identify the repo-native build/test/lint path before Step 1. Check for `CMakeLists.txt`, `compile_commands.json`, `meson.build`, `BUILD`/`WORKSPACE`, `Makefile`, and repo docs. Reuse the canonical configure/build/test/lint commands for each later step instead of rediscovering them.
AI teammates for your engineering loop. Broccoli turns Linear tickets into shipped PRs — powered by Claude and Codex, running on your own Google Cloud.
Repo: besimple-oss/broccoli
Other skills on broccoli.
- /besimple-broccoli-blind
Non-interactive wrapper: plan-sketch -> auto-pick recommended options -> plan-write -> plan-critique-loop -> implement-from-plan -> claude-simplify-wrapper -> dedup -> code-review-loop. No PR creation and no Linear comments.
Open skill - /besimple-tiny-broccoli
Small-change wrapper: implement → run repo checks → atomic commit → run dedup (BASE_SHA..HEAD).
Open skill - /claude-simplify-wrapper
Run Claude's built-in /simplify skill on BASE_SHA..HEAD, validate checks, and commit.
Open skill - /code-review-loop
Iterative review+fix loop for BASE_SHA..HEAD: generate findings, apply accepted fixes, run checks, commit, and re-review up to 3 iterations or until clean.
Open skill - /dedup
Dedupe-only pass for BASE_SHA..HEAD: remove duplicate code introduced by the diff or reuse existing shared utils; applies changes + commits.
Open skill - /plan-critique-loop
Critique and revise an existing plan doc up to 3 iterations, using accept/reject triage and stopping early when no important feedback remains. Use when refining a plan/*.md before implementation.
Open skill

