Agent skill
context-status
Checks current context window usage and provides recommendations. Use when sessions feel slow, responses seem degraded, or before starting complex work.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/context-status
SKILL.md
Context Status
Monitor context window health. Saturation causes degraded performance, forgotten instructions, and tool neglect.
When to Use
- Session feels "slow" or less sharp
- Before complex multi-step task
- After loading many files
- Noticing instructions being forgotten
- Periodically (every 30-60 minutes)
Saturation Symptoms
| Symptom | Severity |
|---|---|
| Forgetting earlier instructions | High |
| Not using mentioned tools | High |
| Repeating completed work | Medium |
| Simplified responses | Medium |
| Missing analysis details | Critical |
Context Levels
| Level | Indicators | Action |
|---|---|---|
| Low | Session <15min, few files | Continue normally |
| Medium | 15-45min, moderate files | Monitor, delegate more |
| High | 45-90min, many files | /checkpoint, strongly delegate |
| Critical | >90min, heavy loading | /compact immediately |
Quick Self-Test
- Can recall safety rules?
- Can recall available tools?
- Can recall agent spawn criteria?
- Remember current task objective?
If any unclear → context likely saturated.
Output
## Context Status
**Level**: [Low/Medium/High/Critical]
**Session Duration**: [estimate]
### Retention Check
- Safety rules: [clear/fuzzy]
- Tool awareness: [clear/fuzzy]
- Task objective: [clear/fuzzy]
### Recommendation
[continue/checkpoint/compact]
### Suggested Action
[specific next step]
Preservation Strategies
- Delegate: Spawn agents → receive summaries (not raw content)
- Query lazily: Ask Doc Agent questions (don't load full docs)
- Progressive disclosure: Return structure + excerpts (not full files)
- Checkpoint regularly: Every major milestone
Related
| If Level | Action |
|---|---|
| Low | Continue normally |
| Medium | /checkpoint before complex work |
| High | Consider /compact, delegate heavily |
| Critical | /compact immediately |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
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?