agentleFS
Sign inStart free
hamzafarooqhamzafarooq/claude-code-starter/.claude/skills/boris-plan/SKILL.md

boris-plan

Skill145 starsChanged 6 months agoMITView on GitHub

Run Boris Cherny's plan-first workflow — write a complete plan, get explicit approval, then execute. Use at the start of any complex task to avoid wasted work and mid-session corrections. Named after Boris Cherny, creator of Claude Code.

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask the user: "Describe the task you want to accomplish."

    line 8

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

This skill enforces the workflow Boris Cherny (creator of Claude Code) uses for every complex task: plan first, execute second, verify last. Credit: Boris Cherny via howborisusesclaudecode.com.

Ask the user: "Describe the task you want to accomplish."

Then produce a plan — do NOT write any code or make any changes yet:

Plan: [Task Name]

What I understand you want

One sentence restatement of the goal. Flag any ambiguity here before proceeding.

Assumptions I'm making

List every assumption. If any are wrong, this is the time to correct them.

What I will do (step by step)

Numbered list. Each step is specific enough that you can verify it happened.

  1. [Step 1 — what file/thing will change and how]
  2. [Step 2]
  3. [Step 3] ...

What I will NOT do

Explicitly name things that are out of scope — adjacent improvements, refactors, style changes — that you might expect but aren't in this plan.

How we'll verify it worked

Specific check: a command to run, a behavior to observe, a test that should pass.

Estimated scope

[Small: <30 min | Medium: 30–90 min | Large: >90 min] — and why

Waiting for your approval before writing a single line.

Reply "approved", suggest changes, or ask questions. Only after approval will execution begin.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free