Context: What problem are we solving? What's the current state?
Changes: Specific files and modifications, with line references
Dependencies: What must happen in order? What can be parallelized?
Verification: How do we confirm success? What tests to run?
Risks: What could go wrong? How do we recover?
Scope Management
Plans should match the request exactly:
If asked to fix a bug, don't refactor surrounding code
If asked to add a feature, don't add "nice to have" extras
If asked to refactor, don't fix unrelated issues you notice
Document out-of-scope observations separately if important
When Plans Get Rejected
Common reasons for plan rejection:
Too vague (no specific file/line references)
Too broad (scope creep beyond the request)
Missing verification steps
Ignoring existing patterns in the codebase
Proposing changes to unread code
Converted and distributed by TomeVault — claim your Tome and manage your conversions.
1---2name: bendrucker-claude-guidelines3description: Planning Guidelines4---56# Planning Guidelines78@references/guidelines.md910## Extended Guidance1112### Reading Before Planning1314Before proposing any changes:15161. Read the files you intend to modify172. Understand the existing patterns and conventions183. Identify related code that might be affected194. Check for existing tests that cover the area2021### Plan Structure2223A good plan includes:2425- **Context**: What problem are we solving? What's the current state?26- **Changes**: Specific files and modifications, with line references27- **Dependencies**: What must happen in order? What can be parallelized?28- **Verification**: How do we confirm success? What tests to run?29- **Risks**: What could go wrong? How do we recover?3031### Scope Management3233Plans should match the request exactly:3435- If asked to fix a bug, don't refactor surrounding code36- If asked to add a feature, don't add "nice to have" extras37- If asked to refactor, don't fix unrelated issues you notice38- Document out-of-scope observations separately if important3940### When Plans Get Rejected4142Common reasons for plan rejection:4344- Too vague (no specific file/line references)45- Too broad (scope creep beyond the request)46- Missing verification steps47- Ignoring existing patterns in the codebase48- Proposing changes to unread code4950---51> Converted and distributed by [TomeVault](https://tomevault.io/claim/bendrucker) — claim your Tome and manage your conversions.52<!-- tomevault:4.0:skill_md:2026-04-11 -->
Run npx skillmds@latest add tomevault-io/bendrucker-claude-guidelines in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Planning Guidelines It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.