메뉴
Perform, resume, refresh, validate, or synthesize the governed DevForgeAI enterprise audit across Prompts 0–8 with immutable provenance. Use for framework skills, hooks, commands, agents, process gates, Claude/Codex parity, and Codex-native behavior.
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
Independently validate a pull request from another AI session before a human merge. Enforce CI/head-SHA triage, an isolated review worktree, repository gates, negative-path proof for guards, reproduced findings, a three-tier verdict, cold fix handoff, delta review, and an explicit merge-or-hold outcome. Use for delegated builder PR review, fix delta review, or agent-work validation. Do not use for your own uncommitted diff or a plain human-authored PR without delegation context.
Independently validate a pull request from another AI session before a human merge. Enforce CI/head-SHA triage, an isolated review worktree, repository gates, negative-path proof for guards, reproduced findings, a three-tier verdict, cold fix handoff, delta review, and an explicit merge-or-hold outcome. Use for delegated builder PR review, fix delta review, or agent-work validation. Do not use for your own uncommitted diff or a plain human-authored PR without delegation context.
Execute a rejected pull request's fix round as a cold implementer session. A reviewer found defects and wrote a handoff comment with numbered findings and C0–C7 checkpoints; work that punch list under invariants enforced by a PreToolUse hook and gate scripts — reproduce the reviewer's red before touching the tree, stay inside the handoff's fence, one `F<n>:` commit per finding, record the output of every acceptance criterion, post a closing report, and STOP without merging. Use whenever a review comes back with changes requested and you are handed the PR plus its findings. Do not use it to author the original plan (that is `delegate`), to build a slice from a plan with no prior review (that is `implement-workflow`), or to review someone else's PR (that is `review-workflow`).
Execute a rejected pull request's fix round as a cold implementer session. A reviewer found defects and wrote a handoff comment with numbered findings and C0–C7 checkpoints; work that punch list under invariants enforced by a PreToolUse hook and gate scripts — reproduce the reviewer's red before touching the tree, stay inside the handoff's fence, one `F<n>:` commit per finding, record the output of every acceptance criterion, post a closing report, and STOP without merging. Use whenever a review comes back with changes requested and you are handed the PR plus its findings. Do not use it to author the original plan (that is `delegate`), to build a slice from a plan with no prior review (that is `implement-workflow`), or to review someone else's PR (that is `review-workflow`).
Create Web, GUI, or Terminal design specifications in story, standalone, or extract mode from a customizable brief, brand, and visual direction; generate design.md, implementation artifacts, and web artifacts when the selected target is Web. Use through /create-design when a project needs a design source of truth or an existing mockup must be extracted.
Create Web, GUI, or Terminal design specifications in story, standalone, or extract mode from a customizable brief, brand, and visual direction; generate design.md, implementation artifacts, and web artifacts when the selected target is Web. Invoke explicitly with $spec-driven-design.
| name | auditing-devforgeai |
| description | Perform, resume, refresh, validate, or synthesize the governed DevForgeAI enterprise audit across Prompts 0–8 with immutable provenance. Use for framework skills, hooks, commands, agents, process gates, Claude/Codex parity, and Codex-native behavior. |
Follow references/audit-protocol.md completely. Use the bundled Prompt Suite,
templates, and audit-bundle script for the same nine-phase contract as Codex.
After Prompts 0–8, run audit-content-validate against the exact managed report
directory and audited snapshot. Do not finalize an untouched template,
placeholder, incomplete Appendix B record, incomplete phase map, or synthesis
whose Prompt 0–7 hashes do not match.
For durable intake, call audit-import-completed, then
audit-findings-build. Never mutate archive content to correct a malformed
source; import a new managed copy with correction provenance. Return only the
validated run ID to remediation.
HALT on missing CLI, exit 127, malformed JSON, snapshot drift, or unsupported Confirmed evidence. Audit execution never edits remediation status or closure.
