Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Plan First

ASecurity

Use before any non-trivial code change — a refactor, new feature, migration, or multi-file edit. Investigate the affected code first, produce a concise implementation plan (files to change, approach, risks, test strategy), get the user's confirmation, then execute. Prevents premature edits and surprise blast radius on risky work.

2 stars
0 votes
0 copies
3 views
Added 10/1/2026
ai-agentsgoapi

Works with

claude codeapi

Security Analysis

A100/100

Scanned 10/1/2026

$npx -y skills add matthews-wong/claude-code-plugins --skill plan-first --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Plan First?

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

Security grade badge for Plan First
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/matthews-wong-plan-first/badge)](https://www.skillsdirectory.com/skills/matthews-wong-plan-first)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: plan-first
description: Use before any non-trivial code change — a refactor, new feature, migration, or multi-file edit. Investigate the affected code first, produce a concise implementation plan (files to change, approach, risks, test strategy), get the user's confirmation, then execute. Prevents premature edits and surprise blast radius on risky work.
---

# Plan First

For anything beyond a trivial one-liner, plan before you edit. A short plan up front
catches wrong assumptions, exposes blast radius, and gives the user a cheap point to
course-correct before code is written.

## When to plan first

- Multi-file changes, refactors, new features, or migrations.
- Anything touching shared/core code, public APIs, or config.
- Work where the approach is non-obvious or has real trade-offs.
- Anything irreversible or wide-reaching.

Skip the ceremony for genuinely trivial edits (a typo, a rename in one spot) — planning
there is just friction. Use judgment.

## The workflow

1. **Investigate first.** Read the affected files, understand current behavior, existing
   conventions, callers, and tests. Never plan against a codebase you haven't looked at.
2. **Write a concise plan.** Skimmable, not a wall of text. Sections:
   - **Goal** — one sentence: what and why.
   - **Files to change** — each path + one line on the change.
   - **Approach** — ordered steps; note key decisions and rejected alternatives.
   - **Risks** — breakage, edge cases, irreversible/wide-reaching effects.
   - **Test strategy** — tests to add/run and manual checks; a bug fix gets a test that
     fails before and passes after.
3. **Confirm.** Ask the user to approve or adjust. Do not edit until they approve. Revise
   and re-confirm if they push back.
4. **Execute as agreed.** Implement the approved plan. If a risk materializes or an
   assumption proves wrong mid-way, pause and surface it instead of silently improvising.
5. **Verify.** Run the test strategy and report results honestly, including anything still
   failing or skipped.

## Principles

- Prefer the smallest change that satisfies the requirement (KISS, YAGNI).
- Match the conventions already in the code over your own preferences.
- Make the plan a decision aid for the user, not a formality — surface the real choices.
- This pairs naturally with Claude Code's plan mode (`permissions.defaultMode: "plan"`),
  which enforces read/plan-only until you approve.

Attribution

matthews-wongmatthews-wong
View sourceSee grades on GitHubMore from matthews-wong →
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

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 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', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 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.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, 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.

741 votes
View all in ai-agents →