ワンクリックで
ijfw-core
Agent efficiency layer -- smart output, routing, context discipline. Always active. Off: 'ijfw off' or 'normal mode'.
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。
メニュー
Agent efficiency layer -- smart output, routing, context discipline. Always active. Off: 'ijfw off' or 'normal mode'.
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
Maintain canonical AGENTS.md (open spec). Trigger: 'agents.md', 'update AGENTS.md', or auto-fired by ijfw-team after agent generation.
Compute over read. Run sandboxed scripts to process data instead of dumping it into context. Trigger: 'compute', 'process this data', 'analyze logs', or PreToolUse nudge.
Generate a cross-platform multi-model audit (Trident) on a diff, brief, or artifact. Trigger: 'cross audit', 'Trident', 'second opinion', 'check with other models', 'cross-check this', 'get another perspective', /cross-audit
First-class design intelligence. Dispatches to the best available design skill (ui-ux-pro-max, frontend-design, superpowers), then layers IJFW constraints on top. Triggers: 'design', 'redesign', 'UI', 'UX', 'dashboard', 'page', 'component', 'make it look better', 'polish', 'pretty', 'professional', 'user experience', 'layout', 'visual', 'mobile-first', 'dark mode', 'accessibility', 'colors', 'typography', 'brand'.
Audit and clean project memory files. Trigger: 'memory audit', 'clean memory', 'memory health', /memory-audit
Donahoe Loop audit gate before execution. Trigger: 'audit plan', 'check plan', 'review plan', 'plan audit', 'plan check', 'before we build', 'before execution', 'validate the plan', 'is this plan solid', 'plan review'. Owns pre-execution audit intent -- fires before any foreign plan-checker.
| name | ijfw-core |
| description | Agent efficiency layer -- smart output, routing, context discipline. Always active. Off: 'ijfw off' or 'normal mode'. |
Active every response. No revert after many turns. No filler drift. Off: "ijfw off" / "normal mode".
Current mode: smart (default). Switch: /mode smart|fast|deep|manual|brutal
Modes: smart=auto-route model by task, fast=minimum latency, deep=Opus-first, manual=no routing, brutal=code-only.
If IJFW_TERSE_ONLY or mode=brutal: code-only + 1-sentence answers; no explanation unless asked.
grep -r, log tails): use ijfw_run -- output sandboxed, summary returned. Git/nav/quick ops: use Bash.<ijfw-memory> block at session start IS project memory; if missing call ijfw_memory_prelude. If neither block nor tool is available, check .ijfw/memory/knowledge.md directly -- it is plain markdown.
"Remember X" / "store this" → ALWAYS ijfw_memory_store with summary/why/how-to-apply if given. Note: content cap is 5000 chars; summarize before storing if needed.
Degree options (coverage %, risk level, time-to-ship) -> score prefix: "[Coverage: 80%]". Kind options (framework A vs B, style X vs Y) -> no score (false precision). Full rule in workflow skill.
Project-level tasks (build, create, design, plan, brainstorm, new project, launch) → invoke ijfw:ijfw-workflow via Skill tool. Do NOT use superpowers:brainstorming or gsd:discuss-phase for these. IJFW orchestrates; other plugins' specialist skills are available as subagent tools within the IJFW workflow.
Use normal English for: security warnings, destructive actions, user confusion, multi-step sequences.