He Plan

Create bounded Harness Engineering execution plans from approved specs or issue slices. Use when work needs ordered implementation units, explicit scope boundaries, rollback posture, traceability, and validation gates before code changes.

9 stars 4 forksSoftware Development

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add jscraik/Agent-Skills --skill he-plan
Manual install
git clone --depth 1 https://github.com/jscraik/Agent-Skills.git /tmp/Agent-Skills
mkdir -p ~/.claude/skills
cp -r /tmp/Agent-Skills/Plugins/harness-engineering/skills/he-plan ~/.claude/skills/he-plan

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Harness Engineering Plan

## Philosophy
Plans are execution contracts, not chat checklists. Turn one approved HE slice
into ordered units with source traceability, validation, rollback, risk, and
next-stage authority. Higher-priority instructions and approval boundaries
remain authoritative.

## When to Use
Use after an approved spec, Linear issue, bug report, reframe phase, or
execution slice needs sequencing before code changes. Inspect first, keep one
selected slice, start with 2-3 focused evidence surfaces, and load more only
when sequencing, validation, rollback, or handoff depends on it.

Use professional confidence review mode when the user asks to deepen a plan,
run technical review, review with professional engineering confidence
standards, or supplies the senior software engineering reviewer /
implementation-risk analyst / Codex harness engineer / Skill Factory validation
partner / media artifact operator / adversarial validation partner prompt shape.
The exact prompt "deepen plan and run a technical review" is an operator
correction signal: improve the existing canonical plan, apply professional
technical review, repair fixable-now gaps, and rerun focused artifact-shape,
BLUF, traceability, and validation gates before handoff.
The long role-stack prompt beginning "You are GPT-5.5 acting as a senior
software engineering reviewer, systems architect, implementation-risk analyst,
specification maintainer, and adversarial validation partner" plus "Review
Read the full skill on GitHub

Details

Skill name
he-plan
Path
Plugins/harness-engineering/skills/he-plan/SKILL.md
License
Apache-2.0
Repo updated
16 November 2026

FAQ

What does the He Plan skill do?

Create bounded Harness Engineering execution plans from approved specs or issue slices. Use when work needs ordered implementation units, explicit scope boundaries, rollback posture, traceability, and validation gates before code changes.

How do I install the He Plan skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add jscraik/Agent-Skills --skill he-plan. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is He Plan popular?

It lives in jscraik/Agent-Skills, which has 9 GitHub stars and 4 forks.

Related skills

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.