메뉴
Multi-agent adversarial code review — four parallel finders (correctness, contracts, security, resources), with every finding independently attacked by skeptics before it reaches you. Use for "review this", "check my changes", or as a pre-PR gate.
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
Loop-until-dry exhaustive hunt — waves of diverse finders keep sweeping until two consecutive rounds surface nothing new, and every fresh finding faces a three-lens judge panel. Use for "find ALL the bugs", full audits, and edge-case sweeps.
Continuous goal-directed operation across many cycles or sessions — maintains a persistent run file (goal, backlog, journal), executes one backlog item per cycle through the full phase discipline, commits at verified milestones, and keeps cycling. Composable with /loop or scheduled tasks for unattended long runs. Use for "keep working on this", overnight runs, or multi-day builds. Wants a git repository — checkpoint commits are its safety rail; it offers git init once if missing.
Repo-wide mechanical change — four parallel discovery modalities find every site, a two-file pilot proves the instruction before the fan-out, then each file is transformed and independently checked, and the project's own checks run once. Use for "rename X everywhere", "replace API A with B", "apply this fix across the repo". It edits files.
Judge-panel design — three genuinely different approaches (simplicity-first, robustness-first, evolution-first) scored by independent judges and synthesized into one grounded implementation plan. Use for architecture decisions or "how should I build X".
Deep codebase research — five parallel search modalities (names, content, structure, git history, tests), deep-reads of every lead, a cited synthesis, and a completeness critic. Use for "where is X handled", "how does Y work", "what breaks if Z changes". This searches the repo, not the web.
Release-readiness gate — detects the project's build/test/release mechanics, runs the gates (read-only hygiene first, then checks and docs in parallel), then a skeptic attacks the "ready to ship" claim. Use before releasing, deploying, tagging, or publishing. It verifies readiness; it never deploys.
| name | fable-review |
| description | Multi-agent adversarial code review — four parallel finders (correctness, contracts, security, resources), with every finding independently attacked by skeptics before it reaches you. Use for "review this", "check my changes", or as a pre-PR gate. |
| argument-hint | [target] |
The user invoked /fable-review: that is explicit opt-in to workflow orchestration — call the Workflow tool.
git status and git diff --stat HEAD to see what is pending; if the tree is clean, target the most recent commit. If the project is not a git repository, target the files the user named or the most recently modified source files.fable-review with args: { target: "<precise description of the change set>", votes: 3 }. If the user asked for a thorough or audit-grade review, use votes: 5.file:line. Note how many raw findings the skeptics refuted (so the user knows the list is filtered), and name anything the review did not cover.If the Workflow tool is unavailable, run the same structure with Agent-tool subagents: four fable-finder agents (one per dimension) in parallel, then three fable-skeptic agents per finding, majority verdict wins.