원클릭으로
findings
Manage the findings register. Log findings, review patterns, triage open items, track refinement effectiveness.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Manage the findings register. Log findings, review patterns, triage open items, track refinement effectiveness.
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
Behavioral floor management. Propose changes, review proposals, apply approved changes, view status. Routes to COO as behavioral floor guardian.
Compliance program management. Propose changes, review proposals, apply approved changes, audit conformance, view change log.
Generic floor management. Routes to the declared guardian for any governance floor. Use /floor propose <floor-name> <change> to propose changes to any active floor.
Structured agent-to-agent handoff. Validates artifact, logs metrics event, dispatches receiving agent.
Run a retrospective for the last completed work item. Pulls DORA metrics, summarizes flow, captures keep/stop/start.
Interactive project setup: copy templates, configure fleet, define compliance floor, add first specialist agent.
| name | findings |
| description | Manage the findings register. Log findings, review patterns, triage open items, track refinement effectiveness. |
| argument-hint | [log <text>|review|patterns|triage] |
Manage the findings register as defined in .claude/COLLABORATION.md § Learning Through Findings.
/findings log "Handoff from backend lacked schema diff" -- Log a new finding/findings log "Handoff from backend lacked schema diff" --urgency high --category boundary-tension -- Log with metadata/findings review -- SM reviews open findings, groups by pattern, proposes refinements/findings patterns -- Analyze recurring finding types and refinement effectiveness/findings triage -- Route unprocessed findings to the appropriate agentParse arguments. Extract the finding description, urgency (default: normal), and category (default: infer from description).
Format the finding. Create an entry using the register format from .claude/findings/register.md:
### [DATE] [URGENCY] -- [BRIEF TITLE]
**Found by:** [current agent or user]
**Category:** surprise | pattern | boundary-tension | learning | success
**Description:** [what happened]
**Proposed action:** [what should change]
**Status:** open
Append to register. Add the entry under "## Active Findings" in .claude/findings/register.md.
Acknowledge. Confirm the finding was logged with its urgency. If urgency is critical, alert: "Critical finding logged. Escalate immediately per protocol."
Read the register. Load .claude/findings/register.md.
Dispatch SM agent. The scrum-master reviews open findings:
Present to user. Show grouped findings with SM's proposals. Wait for user to approve, modify, or defer each proposal.
Apply approved changes. Update finding statuses in the register. If a refinement changes agent behavior, note which agent definition or memory needs updating.
Read the register. Load .claude/findings/register.md.
Analyze. Count findings by category, by urgency, by status. Identify:
Report. Present a structured summary with trend indicators.
Read the register. Filter for Status: open findings.
Route each finding. Based on category and content, recommend which agent should own the response:
Present routing recommendations. User confirms or adjusts.
| Subcommand | Model | Rationale |
|---|---|---|
/findings log | Sonnet | Structured formatting, minimal judgment |
/findings review | Opus | Judgment: pattern analysis, refinement proposals |
/findings patterns | Sonnet | Data aggregation, structured reporting |
/findings triage | Sonnet | Routing logic, structured output |
Implementers can override to add domain-specific finding categories (e.g., "compliance-gap", "performance-regression") or integrate with external issue trackers.