Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Executing Plans

ASecurity

Use when an implementation plan already exists. Execute it in a separate session with review checkpoints.

15 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentspythongit

Works with

claude code

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add AidALL/ghost-alice --skill executing-plans --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Executing Plans?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Executing Plans
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aidall-executing-plans/badge)](https://www.skillsdirectory.com/skills/aidall-executing-plans)

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: executing-plans
description: Use when an implementation plan already exists. Execute it in a separate session with review checkpoints.
calls:
  - "hard:finishing-a-development-branch"
  - "hard:using-git-worktrees"
compatibility:
  - "Python 3.11+ standard library"
---

# Executing Plans
## Contents

- [Overview](#overview)
- [Process](#process)
  - [Step 1: Load and review the plan](#step-1-load-and-review-the-plan)
  - [Step 2: Execute the tasks](#step-2-execute-the-tasks)
  - [Step 2.1: Keep the plan current](#step-21-keep-the-plan-current)
  - [Step 3: Finish development](#step-3-finish-development)
- [Failure modes and cautions](#failure-modes-and-cautions)
- [When to stop and ask for help](#when-to-stop-and-ask-for-help)
- [When revisiting an earlier step](#when-revisiting-an-earlier-step)
- [Things to remember](#things-to-remember)
- [Integration](#integration)


## Overview

Load the plan, review it critically, execute every task, and report on completion.

Announce at the start: "I'm using the executing-plans skill to implement this plan."

Note: when running on a platform that supports subagents (Claude Code, Codex, and so on), use coding-convention:subagent-driven-development instead of this skill. Execution efficiency is much higher in an environment with subagent access.

## Process

### Step 1: Load and review the plan

1. Read the plan file.
2. Review it critically. Identify questions or concerns about the plan.
3. If there are concerns: discuss them with the user partner before starting.
4. If there are no concerns: create the TodoWrite and proceed.

### Step 2: Execute the tasks

For each task:
1. Mark it in_progress.
2. Follow each step exactly (the plan is composed of bite-sized steps).
3. Run verification as specified.
4. Mark it completed.

### Step 2.1: Keep the plan current

If execution or verification proves the plan's scope, order, expected behavior, or task wording is wrong, update the plan before continuing. The plan is the current execution contract, not a log of earlier attempts.

- Edit the existing task text so it reflects the current decision.
- Do not append changelogs, past rationale, previous attempts, or case notes.
- Keep only information needed for future execution: current scope, order, commands, acceptance criteria, and open blockers.
- After editing task text or order, update the active TodoWrite/task tracker so it matches the revised plan before continuing.
- If the change widens or narrows the committed objective, stop and confirm before editing the plan.

### Step 3: Finish development

When every task is completed and verified:
- Announce: "I'm using the finishing-a-development-branch skill to complete this work."
- Required sub-skill: use coding-convention:finishing-a-development-branch.
- Follow that skill to verify, present options, and execute the choice.

## Failure modes and cautions

- Do not mistake the plan file for execution commands.
- Do not arbitrarily add files, tests, or refactors that are not in the plan.
- Do not pass over a blocking situation by guessing.
- Do not skip verification before completion or the finishing-a-development-branch call.

## When to stop and ask for help

Stop execution immediately in the following situations:
- A blocking situation occurs (a missing dependency, a test failure, an unclear instruction).
- The plan has a critical gap that prevents starting.
- You do not understand an instruction.
- Verification fails repeatedly.

Asking clearly is better than guessing.

## When revisiting an earlier step

When returning to review (Step 1):
- The partner updates the plan based on feedback.
- The base approach needs to be reconsidered.

Do not force your way through a blocking situation. Stop and ask.

## Things to remember

- Review the plan critically first.
- Follow the plan steps exactly.
- Do not skip verification.
- Use a skill when the plan references it.
- When blocked, stop and do not guess.
- Do not start implementation on the main/master branch without explicit user consent.

## Integration

Required workflow skills:
- coding-convention:using-git-worktrees - required: set up an isolated workspace before starting.
- coding-convention:writing-plans - writes the plan that this skill executes.
- coding-convention:finishing-a-development-branch - finishes development after every task is complete.

Attribution

AidALLAidALL
View sourceMore from AidALL →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

695601 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →