He Linear Plan

Convert approved HE cognition into small live-ready Linear execution tracking. Use when strategy, reframe, plan, bug, or source-prompt evidence needs scoped issue, milestone, or project routing with explicit confirmation before any live mutation.

9 stars 4 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add jscraik/Agent-Skills --skill he-linear-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-linear-plan ~/.claude/skills/he-linear-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 Linear Plan

## Philosophy

Linear is execution state; `.harness` is cognition and proof. Turn approved HE
cognition into the smallest useful Linear execution slice and make live mutation
status explicit. A local plan must never masquerade as a created issue, bug,
milestone, parent tracker, or live project mutation.

Decision records are upstream cognition, not backlog. When source artifacts
imply architecture-shaping, governance-defining, moat-critical, or
expensive-to-reverse decisions, preserve or request compressed ADR evidence
before routing execution. Do not convert missing ADR reasoning into Linear issue
volume.

## When to Use

Use when approved `.harness` cognition needs Linear routing: destination,
existing project match, milestone/parent shape, sub-issues, dependencies, eval
gates, labels, priority, project/cycle justification, and human/agent route.
Also use when an HE prompt asks to convert ADRs, reframe programs, strategy, or
core invariants into a small Linear execution plan.

## When Not to Use

Do not generate strategy, reframe programs, specs, implementation plans,
implementation work, architecture reviews, eval closure, unfiltered backlog, or
ADR spam. If required decision evidence is absent, route to the appropriate
upstream cognition step or mark the Linear plan blocked instead of inventing
architecture memory inside Linear.

## Inputs

Approved `.harness/**` cognition, repo scope, source-prompt coverage evidence,
Read the full skill on GitHub

Details

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

FAQ

What does the He Linear Plan skill do?

Convert approved HE cognition into small live-ready Linear execution tracking. Use when strategy, reframe, plan, bug, or source-prompt evidence needs scoped issue, milestone, or project routing with explicit confirmation before any live mutation.

How do I install the He Linear Plan skill?

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

Is He Linear 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 ai, llms & agents skills, or write your own with the skills generator.