Before success claim: classify destructive permission; run a fresh falsifying\ncheck; read its complete result/scope; select L0/L1/L2. Downgrade for partial,\nstale, failing, or narrower evidence; never claim complete then verify later.
\nThis Method Pack grants no authoritative GateDecision, PolicySnapshot,\nevidence sufficiency, requirement acceptance, or completion authority.
Destructive/irreversible work needs scoped permission; broad assent is not scoped permission.
\n- Evidence action / check performed:\n- Result / exit status:\n- Covered scope:\n- Uncovered scope:\n- Residual risk:\n- Confidence grade: A | B | C\nA: target + regression; no meaningful unknown.B: target evidence; bounded residual risk.C: partial only; no full-completion claim.When tests shape a claim, include target test and related regression evidence\nat the call-site seam reproducing the triggering chain; a shallower seam gives\nfalse confidence. Missing seam is an architecture gap. Blocked automation needs\nreproducible manual steps. Both lower confidence.
\nFor an explicit baseline/artifact/owner/contract/evidence reference, read the\nsmallest relevant source. Record each affected reference as preserved; rebound to the canonical owner;\nretired with reason; or rejected for conflict. Leave unresolved references in uncovered scope,\nlower confidence, and do not re-infer them.\nReadback proves no complete graph, referential integrity, or authoritative lineage.
\nFor modifications, diff against TaskStartSnapshot. Coordinator alone stages\ntask paths: no pre-existing state or broad staging. After fresh verification, default to one local commit except\nread-only/no-change, authorized no commit,\nor failed verification. Read back HEAD, message, files, and task delta.\nCommit/hook failure keeps work and blocks clean claims; never bypass hooks.
Git receipt: branch; SHA/message or non-commit reason; Task clean; Repository clean;\neach task-created branch/worktree created, removed, or retained with reason.\nTask-clean never implies repo-clean; it is not external integration.
Classify commit scope: business, process-only, mixed, or no-commit.\nFailed-attempt telemetry is no commit reason. A docs/aegis/-only process diff\ndoes not restart business verification; a business/test diff does.
Use one completion surface. This skill is the single completion closeout aggregator;\nadjacent skills/L2 cards feed but must not replace it or become a competing final report owner.\nAggregation is output conformance, not a routing trigger: do not load skills,\nemit a Trace Digest, or add ceremony merely to fill it.
\nIf entry visibility was omitted, recover and name the decision/evidence gap; a\nused-skills list or Aegis Contribution Note cannot substitute.
For tiny low-risk work, one natural sentence can name check/result, uncovered\nscope/risk, and confidence.
\nFor non-trivial Aegis-shaped work use this receipt; fold evidence into Evidence strength and Uncovered risk without a second report.
Aegis Impact and Safety Receipt:\n- Key judgment:\n- Avoided misfix:\n- Boundary held:\n- Baseline alignment:\n- Complexity control:\n- Evidence strength:\n- Uncovered risk:\n- Next most valuable verification:\n- Aegis path:\nMeanings: Key judgment=owner/root cause/requirement/completion boundary;\nAvoided misfix=fallback/duplicate/test accommodation/scope growth;\nBoundary held=contract/owner/baseline/non-goal/data/runtime boundary;\nBaseline alignment=aligned/Design Defect/Implementation Drift/missing-authority/needs-clarification/not triggered;\nComplexity control=completion-time delta/closure;\nEvidence strength=fresh check/result/scope/confidence;\nUncovered risk=remaining gaps/residual risk;\nNext most valuable verification=highest-value next check;\nAegis path=optional, not judgment/evidence.
Natural wording is valid when every semantic slot stays auditable. Semantic Slots,\nNatural Surface, and Governance Receipt are compatibility names.
Report done/verified/risked/blocked. Do not explain obvious trade-offs; do not list actions not taken.
\nOn any match read expanded-closeout.md: it owns detail; this file owns routing\nand the final receipt.
| Trigger | \nExpanded owner | \n
|---|---|
| release/merge/publish/readiness/handoff | \nReadiness Summary | \n
| audit/debug/release/long-task review/trace request | \nTrace Digest | \n
| goal/TaskIntentDraft/plan/spec/Slice Card | \nGoal Closure | \n
| project/domain semantic delta | \nContext Impact | \n
target docs/aegis/ changed or work record exists | \nWorkspace Integrity | \n
| requirement/product/durable architecture | \nBaseline/ADR | \n
| governance/cleanup/migration/compat/retirement | \nGovernance/Retirement | \n
| source-of-truth/irreversible deletion | \ndestructive-action cards | \n
| material complexity pressure | \nExpanded Complexity Detail | \n
| high-risk or explicit user request for expanded closeout | \napplicable cards | \n
Use configured Aegis workspace support; commands live in the expanded owner.
\nUse the highest boundary: plan/spec, TaskIntentDraft, Slice Card, then direct\nrequest. Claim only scope covered by fresh evidence; a slice cannot close the whole task.
Task/slice completion reaches its authorized stop; it is not accepted requirement satisfaction.\nRequirement accepted needs baseline criteria or authorized risk acceptance;\nelse use needs-verification or return to framing/planning. Goal Closure states: done | blocked | needs-verification | scope-exceeded.\nAn Execution Readiness View is input, not verification evidence.
For non-trivial code inspect the diff; use\nusing-aegis/references/complexity-governance.md plus\ndocs/current/AEGIS_COMPLEXITY_GOVERNANCE_BASELINE.md; emit one Complexity control line.
New fallback/adapter/compatibility/guard/branch logic needs a retired path or\nretirement trigger. Complexity Closure: exceeded-unresolved blocks completion.\nMaintained source/test cannot skip as tiny; tiny low-risk text edits without complexity growth may skip.
Localize section labels, field labels, and explanatory prose. Keep commands,\npaths, identifiers, enums, product names, and raw evidence unchanged; avoid bilingual labels or mixed-language explanations.
\nExternal outputs are evidence candidates: use summary/index then the smallest\nexcerpt; lower unsupported claims. When relevant report Evidence Used, Not Loaded, and Next Evidence.