Auditable Playbook Designer
cursor/plugins
Designs a step-by-step playbook for large or unfamiliar work, runs it as a loop of hypotheses and measurements, and logs decisions so a human can review them later.
Works through the task files of a feature's implementation plan one at a time, with a TODO list and a verification step and commit for each task.
Install Execute Implementation Plan
The automated check flagged lines worth reading first. See the safety section below.
$ npx skills add imbue-ai/bouncer --skill execute-implementation-plan -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install imbue-ai/bouncer execute-implementation-plan --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/imbue-ai/bouncer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/execute-implementation-plan .claude/skills/execute-implementation-plan && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "execute-implementation-plan" agent skill from https://github.com/imbue-ai/bouncer/tree/main/.claude/skills/execute-implementation-plan into .claude/skills/execute-implementation-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execute-implementation-plan", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/imbue-ai/bouncer/tree/main/.claude/skills/execute-implementation-planType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add imbue-ai/bouncer --skill execute-implementation-plan -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install imbue-ai/bouncer execute-implementation-plan --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/imbue-ai/bouncer.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/execute-implementation-plan .agents/skills/execute-implementation-plan && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "execute-implementation-plan" agent skill from https://github.com/imbue-ai/bouncer/tree/main/.claude/skills/execute-implementation-plan into .agents/skills/execute-implementation-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execute-implementation-plan", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add imbue-ai/bouncer --skill execute-implementation-plan -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install imbue-ai/bouncer execute-implementation-plan --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/imbue-ai/bouncer.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/execute-implementation-plan .cursor/skills/execute-implementation-plan && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "execute-implementation-plan" agent skill from https://github.com/imbue-ai/bouncer/tree/main/.claude/skills/execute-implementation-plan into .cursor/skills/execute-implementation-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execute-implementation-plan", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/imbue-ai/bouncer.git --path .claude/skills/execute-implementation-plan--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add imbue-ai/bouncer --skill execute-implementation-plan -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install imbue-ai/bouncer execute-implementation-plan --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/imbue-ai/bouncer.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/execute-implementation-plan .gemini/skills/execute-implementation-plan && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "execute-implementation-plan" agent skill from https://github.com/imbue-ai/bouncer/tree/main/.claude/skills/execute-implementation-plan into .gemini/skills/execute-implementation-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execute-implementation-plan", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install imbue-ai/bouncer execute-implementation-planInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add imbue-ai/bouncer --skill execute-implementation-plan -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/imbue-ai/bouncer.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/execute-implementation-plan .github/skills/execute-implementation-plan && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "execute-implementation-plan" agent skill from https://github.com/imbue-ai/bouncer/tree/main/.claude/skills/execute-implementation-plan into .github/skills/execute-implementation-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execute-implementation-plan", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add imbue-ai/bouncer --skill execute-implementation-plan -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install imbue-ai/bouncer execute-implementation-plan --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/imbue-ai/bouncer.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/execute-implementation-plan .opencode/skills/execute-implementation-plan && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "execute-implementation-plan" agent skill from https://github.com/imbue-ai/bouncer/tree/main/.claude/skills/execute-implementation-plan into .opencode/skills/execute-implementation-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execute-implementation-plan", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
execute-implementation-plan- GitHub stars
- 400
- Token cost
- ~425 tokens
- SKILL.md length
- 184 words
- Files
- 2
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Works through the task files of a feature's implementation plan one at a time, with a TODO list and a verification step and commit for each task.
- Works in 2 steps: Read the overview file at… → Build the TODO list from the Task Index…
- Carrying out a written implementation plan split into numbered task files
- SKILL.md covers Input, Before starting, Executing tasks and Do not
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Given a feature name, this skill first reads only the 00_overview.md file in that feature's implementation_plan folder under docs. From the Task Index table it builds a TODO list with one entry per row, each phrased as read and execute that task file, and it holds off on reading the task files themselves.
The agent then takes the entries in order: mark one in progress, read its task file, follow the bundled implement_task.md to implement, verify, self-review and commit, mark it complete and move on. The rules forbid skipping verification, committing while verification fails and moving past a failed task without asking. When a task hits a hard blocker the agent cannot resolve, it stops and asks you how to proceed.
When your agent uses it
- Carrying out a written implementation plan split into numbered task files
- Running a plan in which every task must be verified and committed before the next
- Stopping a long plan for your decision when one task fails
Example prompts
- “Execute the implementation plan for the dark-mode feature.”
- “Work through the my-feature implementation plan task by task.”
- “Run the payments-refactor plan and stop if any task fails verification.”
Requirements
- An implementation_plan folder under the feature's docs directory, starting with 00_overview.md
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- Read the overview file at docs/$ARGUMENTS/implementation_plan/00_overview.md. This is the ONLY file you read right now — do not read any…
- Build the TODO list from the Task Index table in the overview. For each row, create a TODO entry with this exact format
What it can do on your machine
Read from SKILL.md and the folder at commit 1ed480c. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Execute Implementation Plan loads about 425 tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 184 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: warnings
The automated check found patterns that need a careful read before installing.
- WarningTells the agent its actions are pre-authorized / not to stop for confirmationSKILL.md:46
- Proceed past a failed task without asking the user
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from imbue-ai/bouncer at commit 1ed480c, republished under its AGPL-3.0 licence (© imbue-ai). 184 words, ~425 tokens.
Download SKILL.mdSave it as
.claude/skills/execute-implementation-plan/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- execute-implementation-plan
- description
- Execute an implementation plan by working through each task file in order. Use when an implementation plan folder exists at docs/<feature>/implementation_plan/.
- disable-model-invocation
- true
- argument-hint
- <feature-name>
Execute Implementation Plan
Input
Feature name: $ARGUMENTS
Before starting
Read the overview file at
docs/$ARGUMENTS/implementation_plan/00_overview.md. This is the ONLY file you read right now — do not read any task files yet.Build the TODO list from the Task Index table in the overview. For each row, create a TODO entry with this exact format:
Read and execute docs/$ARGUMENTS/implementation_plan/<filename>For example:
- "Read and execute docs/my-feature/implementation_plan/01_01_install_diffs.md" — pending
- "Read and execute docs/my-feature/implementation_plan/01_02_replace_changes_tab.md" — pending
- "Read and execute docs/my-feature/implementation_plan/02_01_add_config_fields.md" — pending
Executing tasks
Work through the TODO list in order. For each entry:
- Mark it as in_progress
- Read the task file specified in the TODO entry
- Follow the instructions in
.claude/skills/execute-implementation-plan/implement_task.mdto implement, verify, self-review, and commit the task - Mark it as completed
- Move to the next entry
If a task fails with a hard blocker you cannot resolve, stop and ask the user how to proceed.
Do not
- Read task files ahead of time — only read each task file when you start working on it
- Skip verification steps
- Commit if verification is failing
- Proceed past a failed task without asking the user
© imbue-ai, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .claude/skills/execute-implementation-plan of imbue-ai/bouncer.
- SKILL.md
- implement_task.md
Open the folder on GitHubat commit 1ed480c
Compare with similar skills
Execute Implementation Plan next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Execute Implementation Plan this skillimbue-ai/bouncer | 400 | — | ~425 | Automated safety check: Warn | AGPL-3.0 | |
| Auditable Playbook Designercursor/plugins | 10k | 8 repos | ~1k | Automated safety check: Pass | None | |
| Iterative Development Orchestratorprime-radiant-inc/iterative-development | 181 | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| Fable Disciplineassafkip/kipi-system | 112 | — | ~2.9k | Automated safety check: Pass | MIT | |
| Spec-Driven DevelopmentLichAmnesia/lich-skills | 234 | — | ~3.5k | Automated safety check: Pass | MIT | |
| Launch Delivery PipelineYeachan-Heo/oh-my-claudecode | 40k | — | ~7.3k | Automated safety check: Pass | MIT |
Similar skills
- Official
Iterative Development Orchestrator
prime-radiant-inc/iterative-development
Runs an autonomous loop that extracts requirements with proof obligations, builds a walking skeleton, then audits sprint by sprint against real behavior evidence.
Fable Discipline
assafkip/kipi-system
Teaches staged, verifiable coding habits for multi-file tasks and ships a hook that blocks tests from touching live data.
Spec-Driven Development
LichAmnesia/lich-skills
Runs a gated Spec, Plan, Build, Test, Review, Ship workflow so non-trivial changes are specified, verified and reviewed before they ship, with a named artifact per phase.
Launch Delivery Pipeline
Yeachan-Heo/oh-my-claudecode
Delivery pipeline from mission brief to verified change: writes a spec, splits it into tickets, runs them in parallel, verifies and reports a decision log after a repo audit gate.
Superpowers
Peiiii/nextclaw
A skill your agent uses when the user wants a disciplined software development workflow with design-first planning, implementation plans, TDD, systematic debugging, code review, or…
More from imbue-ai/bouncer
HTML Feature Mocks
imbue-ai/bouncer
Explores a feature idea through HTML mocks that match the project's existing UI, keeping every earlier version and logging each requested tweak in a context file.
Implementation Plan Writer
imbue-ai/bouncer
Turns a feature's goals, requirements and architecture documents into a set of self-contained task files that a developer with no project context can follow.
Requirements From HTML Mocks
imbue-ai/bouncer
Turns an HTML mock iteration session into a requirements document that describes only user-facing behavior.
Architecture Document Writer
imbue-ai/bouncer
Writes an architecture document for a feature from its goals and requirements, after asking questions and studying the existing codebase.
Related
Categories
Questions about Execute Implementation Plan
What does Execute Implementation Plan do?
Works through the task files of a feature's implementation plan one at a time, with a TODO list and a verification step and commit for each task. md file in that feature's implementation_plan folder under docs. From the Task Index table it builds a TODO list with one entry per row, each phrased as read and execute that task file, and it holds off on reading the task files themselves.
When should I use Execute Implementation Plan?
Execute Implementation Plan fits situations like: carrying out a written implementation plan split into numbered task files; running a plan in which every task must be verified and committed before the next; stopping a long plan for your decision when one task fails.
How do I install Execute Implementation Plan in Claude Code?
Run `npx skills add imbue-ai/bouncer --skill execute-implementation-plan -a claude-code`. Or copy the skill folder (.claude/skills/execute-implementation-plan in imbue-ai/bouncer) into .claude/skills/execute-implementation-plan in your project. Claude Code loads it when a task matches its description.
How do I install Execute Implementation Plan in Codex?
Run `npx skills add imbue-ai/bouncer --skill execute-implementation-plan -a codex`. Or copy the skill folder (.claude/skills/execute-implementation-plan in imbue-ai/bouncer) into .agents/skills/execute-implementation-plan in your project. Codex loads it when a task matches its description.
Can I use Execute Implementation Plan in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add imbue-ai/bouncer --skill execute-implementation-plan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/execute-implementation-plan, .gemini/skills/execute-implementation-plan, .github/skills/execute-implementation-plan and .opencode/skills/execute-implementation-plan in your project.
What does Execute Implementation Plan need to run?
SKILL.md names no scripts, command-line tools or credentials: Execute Implementation Plan is instructions for the agent only. Our summary lists: An implementation_plan folder under the feature's docs directory, starting with 00_overview.md.
Does Execute Implementation Plan access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Execute Implementation Plan safe to install?
Our automated static check of SKILL.md flagged 1 warning(s): tells the agent its actions are pre-authorized / not to stop for confirmation. Read the flagged lines before installing; the check is not a guarantee either way.
What licence does Execute Implementation Plan use?
Execute Implementation Plan is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Execute Implementation Plan use?
About 425 tokens (SKILL.md is roughly 1.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Execute Implementation Plan?
Skills that share tags, products or a category with Execute Implementation Plan: Auditable Playbook Designer (cursor/plugins, 10k stars), Iterative Development Orchestrator (prime-radiant-inc/iterative-development, 181 stars), Fable Discipline (assafkip/kipi-system, 112 stars) and Spec-Driven Development (LichAmnesia/lich-skills, 234 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Execute Implementation Plan?
imbue-ai (a GitHub organization) maintains it in imbue-ai/bouncer, which has 400 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 8, 2026.
Source: imbue-ai/bouncer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.