メニュー
Check how much context window remains in this session. Use when you want to know token budget, context usage, or how much room is left before compaction. Also use proactively when working on long tasks to gauge remaining capacity.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Score way matching (embedding and BM25), analyze vocabulary, and validate frontmatter. Use when testing how well a way matches prompts, checking cosine similarity or BM25 scores, inspecting the embedding engine status, or validating way files.
Cite governance controls and justifications when making recommendations about code quality, security, commits, or documentation. Use when justifying why a practice matters, when a user asks "why do we do this?", when reviewing code against standards, or when recommending practices that align with NIST, OWASP, ISO, SOC 2, CIS, or IEEE controls.
Ship current work through the branch → commit → push → PR → merge → cleanup flow. Picks up wherever you are in the cycle. Use when the user says "ship it", "land this", "merge this", or invokes /ship.
Review what changed in Claude Code upstream and compare against this project's commits and ADRs. Surfaces opportunities, gaps, and ADR status drift. Discovery conversation, not compliance dashboard.
Strategy selector for structured reasoning. Lists available thinking frameworks and invokes the right one. Use when facing complex decisions, trade-offs, or when stuck.
Self-Consistency reasoning — run multiple independent reasoning paths and take consensus. Use for high-stakes decisions where reasoning errors are costly.
| name | context-status |
| description | Check how much context window remains in this session. Use when you want to know token budget, context usage, or how much room is left before compaction. Also use proactively when working on long tasks to gauge remaining capacity. |
| allowed-tools | Bash |
Run the context usage command and capture the JSON output:
ways context --json
Then render a visual gauge using the chart tool. Build the JSON and pipe it:
# Parse the values from the --json output, then:
echo '{"type":"hbar","data":{"Used (PCT%)":USED,"Free (RPCT%)":REMAINING},"title":"Context: USEDk / TOTALk tokens (MODEL)","width":60,"format":"human"}' \
| ~/.claude/hooks/ways/softwaredev/visualization/charts/chart-tool
Replace USED, REMAINING, TOTAL, PCT, RPCT, and MODEL with actual values from the JSON output. Use jq to extract them.
The command auto-detects the context window size from the model in the transcript (1M for Opus 4.6, 200k for others). Override with CLAUDE_CONTEXT_WINDOW env var.
If the remaining percentage is below 20%, mention that compaction is approaching and suggest wrapping up or prioritizing remaining work.