ReddRadar
Agent skill
tips
Use when starting a Claude Code session, feeling overwhelmed by context, or needing workflow tips. Triggers on "how do I manage sessions", "context getting long", "remind me".
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/tips
SKILL.md
Claude Code Session Tips
Quick reference for effective Claude Code usage.
Session Management
| Action | How |
|---|---|
| Clear context | /clear (rename first with /rename for easy return) |
| Resume session | claude --resume <session-id> |
| Fork session | claude --continue --fork-session (branch off without modifying original) |
| Clear input area | Esc Esc (double-tap) |
| Clear single line | Ctrl+U (shell shortcut) |
| Stash input | Ctrl+S - saves draft, auto-restores after next submit (#14740, source) |
| Optimize Rules | /claude-md-improver |
Context Hygiene
/clearaggressively - long contexts slow responses/renamebefore clearing to make sessions findable
Quota Management (Max Subscription)
Key insight: Context size counts toward your quota. Each turn re-sends the entire conversation history.
| Context size | Per-turn cost |
|---|---|
| 20k (fresh) | 1x |
| 100k | 5x |
| 180k | 9x |
The rule: If your next question doesn't need previous context, /clear first.
Mid-work one-off questions:
- Option A: Ask parent to spawn subagent → still costs 1 parent turn
- Option B: New Ghostty tab → cheaper IF you use the knowledge implicitly without pasting back
- Best: New tab, absorb answer yourself, continue in parent with informed instructions
Auto-Compact Buffer (source, docs)
Formula: buffer = 13k + maxOutputTokens
CLAUDE_CODE_MAX_OUTPUT_TOKENS |
Buffer | Effective Context |
|---|---|---|
| 22k (more context) | 35k | ~165k |
| 32k (default) | 45k | ~155k |
| 64k (max) | 77k | ~123k |
Trade-off: lower output tokens = more context but shorter max responses.
Theming & Appearance
Toggle CC's syntax theme: /config → Theme → Ctrl+T
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?