ReddRadar
Agent skill
linear-discipline
Use this skill when discussing code changes, implementation work, feature status, or when starting/completing development tasks. Reminds about Linear issue tracking discipline - always having an issue in progress before writing code, marking work as done, and creating issues for unexpected scope. Triggers when users mention implementing features, writing code, or checking on work status.
Install this agent skill to your Project
npx add-skill https://github.com/jclfocused/claude-agents/tree/main/custom_plugins/plugins/linear-planning-workflow/skills/linear-discipline
SKILL.md
Linear Discipline Skill
This skill ensures proper Linear issue tracking discipline is maintained throughout development conversations.
When to Use
Apply this skill when:
- Users mention they're about to start coding something
- Discussing implementation without mentioning a Linear issue
- Users complete work and might forget to update Linear
- Unexpected scope or bugs are discovered during work
- Checking on feature or work status
Core Discipline Rules
Rule 1: No Code Without an Issue
Never write code without a Linear issue in "In Progress" status.
Before any implementation work:
- Ensure a Linear issue exists for the work
- Mark the issue as "In Progress"
- Only then begin writing code
Rule 2: Mark Work Complete Immediately
When work is done, immediately update Linear.
- Commit the code changes
- Mark the Linear issue as "Done"
- Don't batch status updates
Rule 3: Sub-Issues Are Mandatory
A parent issue is NOT done until all sub-issues are done.
- Track progress at the sub-issue level
- Mark each sub-issue "Done" as completed
- Parent issue stays open until all children complete
Rule 4: Create Missing Scope
If you discover work that needs doing but has no issue, create one first.
- Found a bug? Create a bug issue first
- Need to refactor? Create a refactor issue first
- Missing functionality? Create a sub-issue first
Always: Create issue → Mark "In Progress" → Do work → Mark "Done"
Gentle Reminders
When User Says They're Starting Work
"Before we begin, let's make sure there's a Linear issue for this work. Is there an existing issue we should mark 'In Progress', or should we create one?"
When User Completes Something
"Great work! Don't forget to mark the Linear issue as 'Done' to keep tracking accurate."
When Unexpected Work Appears
"This looks like new scope. Let's create a sub-issue for it before we implement it, so it's properly tracked."
Status Flow
Todo → In Progress → Done
↓
(If blocked)
↓
Blocked → In Progress → Done
Plan Mode Integration
When using Claude Code's built-in plan mode, Linear tracking happens automatically:
How It Works
- Plan mode entry - Skill
linear-plan-modeasks if plan should be tracked in Linear - Plan development - As you write the plan file, Linear issues are created/updated
- Plan sections → Sub-issues - Each major section becomes a Linear sub-issue
- Plan finalization - Before ExitPlanMode, ensure all sections have issues
Key Behaviors
- Plan file and Linear stay synchronized throughout planning
- New sections → new sub-issues created
- Modified sections → sub-issues updated
- Removed sections → sub-issues canceled (with confirmation)
Plan Mode Tools
| Tool | Purpose |
|---|---|
linear-mvp-project-creator |
Creates parent issue + sub-issues from plan |
linear-project-context |
Checks for existing feature issues |
linear-plan-sync |
Syncs plan file changes to Linear |
For detailed plan mode workflow, see the linear-plan-mode skill.
Integration with Workflow
This discipline integrates with:
/planFeature- Creates properly structured issues/work-on-feature- Enforces status tracking during executionexecute-issueagent - Automatically manages status transitionslinear-plan-modeskill - Maintains plans in Linear during plan mode
Remember: Linear is the source of truth. Keep it accurate.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
jclfocused/claude-agents
graphite-workflow
Use this skill when working with Graphite (gt) for stacked PRs, using execute-issue-graphite agent, or when the user mentions Graphite, stacking, or gt commands. Ensures proper use of gt commands instead of raw git for stack-aware operations.
jclfocused/claude-agents
vertical-slice-planning
Use this skill when discussing feature breakdown, PR structure, implementation ordering, or how to decompose work. Guides thinking about vertical slices (end-to-end functionality) rather than horizontal layers (all of one layer first). Triggers on "how should we break this down?", "what order should we implement?", "how many PRs?", or decomposition discussions.
jclfocused/claude-agents
issue-writing
Use this skill when writing, reviewing, or discussing issue descriptions, acceptance criteria, or task breakdowns. Ensures consistent, high-quality issue structure that any developer or AI can pick up and execute. Triggers when drafting issues, defining requirements, or when users ask "how should I write this issue?" or "what should the acceptance criteria be?"
jclfocused/claude-agents
mvp-scoping
Use this skill when discussing features, planning work, or when users describe what they want to build. Guides MVP thinking - focusing on "what's the minimum to make this work?" rather than comprehensive solutions. Triggers on phrases like "help me think through this feature", "what should we build first?", "how should we scope this?", or any feature planning discussion.
jclfocused/claude-agents
atomic-design-planning
Use this skill when discussing UI components, design systems, frontend implementation, or component architecture. Guides thinking about Atomic Design methodology - atoms, molecules, organisms - and promotes component reuse over creation. Triggers on UI/frontend discussions, "what components do we need?", "should I create a new component?", or design system questions.
jclfocused/claude-agents
example-skill
Example skill - Claude will autonomously use this based on the description. Describe what this skill does and when to use it.
Didn't find tool you were looking for?