Agent skill
scope-discipline
Use when implementing features, editing source code, or responding to task handoffs. Enforces doing exactly what was requested - no scope creep, no "while I'm here" additions.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/scope-discipline
SKILL.md
Scope Discipline
Hard Rule
Do exactly what the task asks. Nothing more.
Warning Signs
If you catch yourself thinking:
- "While I'm here, I should also..."
- "This would be cleaner if I refactored..."
- "Let me add error handling for edge cases that might..."
- "I'll add a helper function for future use..."
- "This needs better types/documentation..."
- "Let me make this more configurable..."
STOP. Complete the task as specified first. Note improvements in handoff if genuinely valuable.
What Counts as Scope Creep
| In Scope | Out of Scope |
|---|---|
| Fix the bug reported | Refactor surrounding code |
| Add requested feature | Add "nice to have" extras |
| Handle specified cases | Handle hypothetical cases |
| Use existing patterns | Introduce new patterns |
| Modify listed files | "While I'm here" changes |
The Test
Before making a change, ask: "Did the task explicitly ask for this?"
- Yes → Do it
- No, but necessary for task → Do it, explain why
- No, but would be nice → Don't do it. Note in handoff if important.
Recovery
If you've already gone out of scope:
- Revert uncommitted scope creep
- Complete original task
- Propose extras as separate follow-up task
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?