메뉴
Generate candidate EOU refactor options from an audit or incident. Does not apply changes directly.
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
| name | eou-refactor |
| description | Generate candidate EOU refactor options from an audit or incident. Does not apply changes directly. |
Generate candidate refactor options for $target. Do not apply any change.
$target (required) — either an EOU ID (resolved to foundry/eous/{id}.yml or foundry/meta-eous/{id}.yml) or a path to an audit report or diagnosis file. When an audit path is given, the EOU ID is extracted from the report.foundry/refactoring-patterns.yml — canonical refactor types (split, merge, scope-reduction, authority-downgrade, step-extraction, validator-addition, stop-condition-injection, responsibility-separation)foundry/constitution.yml — invariants that constrain any proposed changefoundry/governance.yml — authority boundaries and lifecycle-gate rules; required because refactor options can touch authority_level and blast_radius$target if an audit path is given)Halt and report before generating options if:
$target does not identify an EOU ID and one cannot be inferred.foundry/eous/ or foundry/meta-eous/.$target (EOU ID or audit report). If it is an audit report, extract the EOU ID and load the corresponding spec.foundry/refactoring-patterns.yml.requires_ecp: true.Write to foundry/self-evolution/refactor-options/{eou_id}-refactor-{YYYYMMDD}.yml.
Each option must include:
option_id:
target_failure: # the structural problem this addresses
proposed_change: # one specific modification (not a vague direction)
expected_benefit: # observable improvement
risk: # what can degrade
affected_files: # list of files that would change
tests_required: # regression cases to add or update
rollback_plan: # how to revert
arguments_against: # strongest case for not doing this
requires_ecp: # true | false
Mark requires_ecp: true when the option does any of the following:
authority_levelblast_radius.forbidden_scopeAudit a generated candidate EOU set for boundary quality, minimality, overlap, authority, operational value, and governance risk.
Audit value_invocations in run traces for EOUs with classification.judgment_authorized:true. Verifies invocations against the captured_workflow's declared priority (no F15), checks for drift over multiple runs (no F16), detects hallucinated value ids (no F17), catches silent decisions on contested cases (F14), and runs counterfactual-swap audit as the V1 anti-theater defense.
Audit EOU specs for Foundry V2 faceted classification, authority limits, schemas, validation, failure modes, trace, blast radius, and responsibility ownership.
Synthesize a Stage 0 captured_workflow (D2.4 step 1–5 outputs + per-app constitutional domain_values layer) from a user goal, structured 5-role reference set, and constraints. For users entering an unfamiliar craft domain who cannot articulate a workflow unaided, and for any user who needs the constitutional layer made explicit before downstream EOU generation begins.
Generate a minimal, ranked candidate EOU set from a messy workflow using Foundry V2 constraints. Candidates are proposal-only and cannot be activated.
Audit a generated candidate EOU set for boundary quality, minimality, overlap, authority, operational value, and governance risk before any candidate advances to specification. <example> Context: A generation run has just produced a candidate set; the owner wants to know which candidates survive audit before promotion. user: "$audit-candidate-eou-set foundry/self-evolution/candidate-sets/cs-generate-eou-candidates-20260520-1430.yml" assistant: "I'll run the eight tests (boundary, non-overlap, minimality, authority, operational value, counter-generation, set composition, high-stakes) and write the audit report under foundry/audits/candidate-set-audits/." </example> <example> Context: User wants to audit a candidate set that contains a generating EOU without a corresponding audit path. user: "$audit-candidate-eou-set ./my-candidates.yml" assistant: "I'll audit. Heads-up that if any candidate has authority_level approve/publish or proposes weakening validators, I'll escalate to FAIL regardless of other test outc