Agent skill
scope-management
Manage scope effectively - identify resources, prevent creep, optimise for token budget
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/scope-management-baphled-dotopencode
SKILL.md
Skill: scope-management
What I do
I help manage scope effectively by identifying required resources, preventing scope creep, and optimising scope to fit token budgets. I provide resource data to token-cost-estimation.
When to use me
- Before starting work to define boundaries
- When scope is expanding unexpectedly
- When token budget is constrained
- When identifying what resources are needed
- When deciding what to defer or cut
Core principles
- Define boundaries upfront - What's in, what's out
- Identify resources early - Files, tools, external dependencies
- Say no appropriately - Protect scope from creep
- Optimise for constraints - Fit scope to available tokens
- Defer explicitly - Out-of-scope items get tracked, not forgotten
Resource Identification
Resource Categories
| Category | Token Impact | Identification |
|---|---|---|
| Files to read | ~100-200 per file | List before starting |
| Files to modify | ~200-500 per file | Explicit list |
| Tools required | ~50-100 per call | Identify patterns |
| External lookups | ~200-500 each | Web fetches, docs |
| Context needed | Variable | Prior knowledge required |
Resource Estimation Template
## Resource Requirements
Files to read: X files (~Y tokens)
Files to modify: X files (~Y tokens)
Tool calls expected: ~X calls (~Y tokens)
External lookups: X (~Y tokens)
Context rebuilding: ~Y tokens
Total resource overhead: ~Z tokens
Scope Optimisation
For Token Budget
When tokens are limited:
- Cut nice-to-haves - Essential only
- Defer to next session - Track explicitly
- Reduce file scope - Fewer files = fewer tokens
- Skip verification shortcuts - But document risk
- Use cached knowledge - Check memory-keeper first
Scope Reduction Strategies
| Strategy | Token Savings | Trade-off |
|---|---|---|
| Defer docs | 10-20% | Technical debt |
| Minimal tests | 20-30% | Coverage risk |
| Single file focus | 30-50% | Scope reduction |
| Skip exploration | 20-40% | Miss context |
Scope Creep Prevention
Warning Signs
- "While we're here..." additions
- Discovering "one more thing"
- Requirements expanding mid-task
- Unclear original scope
Response Pattern
SCOPE CREEP DETECTED:
New request: [what]
Original scope: [was]
Options:
1. Add to current (impact: +X tokens)
2. Defer to next session (no impact)
3. Replace existing item (swap)
→ Recommend: [choice with reasoning]
Anti-patterns to avoid
- ❌ Starting without defined scope
- ❌ Saying yes to all additions
- ❌ Not identifying resources upfront
- ❌ Forgetting deferred items
- ❌ Ignoring token budget constraints
KB Reference
~/vaults/baphled/3. Resources/Knowledge Base/AI Development System/Skills/Workflow-Orchestration/Scope Management.md
Related skills
token-cost-estimation- Uses resource data for estimatesestimation- Scope affects estimatestask-tracker- Tasks reflect scopepre-action- Clarify scope before starting
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?