메뉴
Route implementation work to Codex CLI; Claude specs, reviews, verifies.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
Run OpenCandle's repo-local autoreview helper for local branch, PR, or commit review. Use when the user asks for autoreview, PR review, second-model review, or a final closeout review before commit, push, merge, or release.
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.
SOC 직업 분류 기준
| name | codex-first |
| description | Route implementation work to Codex CLI; Claude specs, reviews, verifies. |
Claude Code sessions only. Codex/other harnesses: skip; never self-delegate.
Rationale: Claude (Fable/Opus) tokens metered + expensive; Codex flat-rate. GPT-5.5+ is usually the better and faster model at writing/implementing code; Claude wins at ergonomics — judgment, design, spec-writing, review, orchestration. So Codex types, Claude thinks and verifies.
Delegate to Codex (default for hands-on work):
Keep in Claude:
Mixed task: Claude designs first, freezes spec, delegates build-out.
Heuristic: prompt reads as a work order → delegate; writing it forces decisions → design, Claude.
Portfolio/multi-repo work: $maintainer-orchestrator instead.
Prompt via temp file, never inline quoting:
P=$(mktemp); cat >"$P" <<'EOF'
<goal, repo + key paths, constraints ("don't touch X"), non-goals, proof expected, output shape>
EOF
command codex exec --yolo -C <repo> \
-c model_reasoning_effort="high" \
-o /tmp/codex-last.md - <"$P" 2>/dev/null
--yolo is the house default; Codex may run commands/tests freely. Keep prompts scoped to the target repo.command codex bypasses the interactive zsh wrapper; if not on PATH: fnm exec --using default -- codex2>/dev/null only to debug a failing run-o file for the result; don't parse the JSONL stream-o file on exit; don't kill quiet runs <30 min-o files--skip-git-repo-checkFollow-up fixes — cheaper than fresh runs, keeps context. resume has no -C/--yolo: run from the repo dir, spell the long flag:
(cd <repo> && command codex exec resume --last \
--dangerously-bypass-approvals-and-sandbox \
-o /tmp/codex-last.md - <"$P2" 2>/dev/null)
Codex starts with zero session context. Every prompt: goal, exact repo/paths, constraints, non-goals, proof expected (exact test command), output shape ("report files changed + test output"). Spec quality decides success.
git status -sb + read the full diff; judge like a contributor PR$autoreview before shipWin = generation + exploration tokens moved to Codex; Claude spends only on spec + diff review. Don't ping-pong trivia through delegation; don't re-read what Codex already summarized.