메뉴
This skill should be used when the user says "low token mode", "minimal responses", "short answers only", "save tokens", "be concise", "150 token limit", "stop explaining things", or "I'm running low on context".
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
This skill should be used when the user says "check claude.md size", "is my claude.md too big", "claude.md token cost", "how big is claude.md", or when triggered automatically on session start to warn about oversized claude.md files.
This skill should be used when the user asks to "show recent changes", "show forge changelog", "show changelog for <project>", "what did I add this week", "what files did I touch today", "what packages keep recurring", "what drifts from the template", "review template suggestions", "show pending forge suggestions", "sync forge templates", "apply template suggestion", or "compute back-mapping suggestions". Provides read, drift-discovery, and template back-mapping workflows that wrap the `forge-db` MCP tools (`get_changelog`, `compute_suggestions`, `apply_suggestion`).
This skill should be used when the user says "build a wiki", "maintain a wiki", "ingest docs into wiki", "query my wiki", "set up llm wiki", "wiki-based knowledge base", "stop re-reading docs every session", "persistent knowledge base", or "compress my docs into wiki pages".
This skill should be used when the user says "auto compact", "enable auto compact", "compact on context full", "automatic context compression", "prevent context limit errors", "set up auto compaction", or "context keeps hitting limit".
This skill should be used when the user says "show settings diff", "what changed in settings", "compare settings before after", "settings optimization preview", "preview settings changes", or "show me what tune-settings will change".
Use this skill when the user says "/task_brain", "break down this task", "plan this", "decompose this problem", or when a task has multiple moving parts, unclear dependencies, or high ambiguity.
| name | Low Token Mode |
| description | This skill should be used when the user says "low token mode", "minimal responses", "short answers only", "save tokens", "be concise", "150 token limit", "stop explaining things", or "I'm running low on context". |
| version | 1.0.0 |
Activate a strict response discipline that minimizes token output without losing technical accuracy. Apply when users need to conserve context window budget.
When user requests low token mode, confirm activation and apply ALL rules below immediately:
LOW TOKEN MODE: ON
Max response: 150 tokens
No explanations unless asked.
| Rule | Detail |
|---|---|
| Max response length | 150 tokens |
| No explanations | Skip unless user says "explain" or "why" |
| Code over prose | Prefer code blocks over descriptions |
| No context repetition | Never restate the problem |
| Diff-style edits | Show only changed lines, not full files |
| Skip pleasantries | No "Sure!", "Great question", "Happy to help" |
| One word when possible | "Done." not "I have completed the task." |
Standard answer:
[result only]
Code change:
- old line
+ new line
File edit:
File: path/to/file.py, line 42
Change: `old_value` → `new_value`
Error fix:
Cause: [one line]
Fix: [code or command]
Deactivate when user says "normal mode", "stop low token", "full responses", or "explain everything".
On deactivation:
LOW TOKEN MODE: OFF
Normal responses resumed.
references/token-patterns.md — Response templates for common task types in low token mode