Skip to content
OpenAgentSkill
Browsing is open · Catalog captured 2026-11-21 · Automatic updates and account services are paused.
Browser & automation

verification-before-completion

Use when about to claim work is complete, fixed, passing, verified, release-ready, or ready to commit, merge, publish, or hand off.

GanyuanRan · AI review on file

Installation

Read the source and dependencies before running a command. Copying does not install or execute anything.

npx skills add GanyuanRan/Aegis --skill verification-before-completion

About this skill


name: verification-before-completion description: "Use when about to claim work is complete, fixed, passing, verified, release-ready, or ready to commit, merge, publish, or hand off."

Execute

Before any success claim, classify destructive permission needs, choose and run a fresh falsifying check, read its complete result/scope, then select L0/L1/L2. If evidence is partial, stale, failing, or narrower than the claim, downgrade; never claim complete first and verify later.

This Method Pack grants no authoritative GateDecision, PolicySnapshot, evidence sufficiency, requirement acceptance, or completion authority.

Stop Signals

Stop before claiming or advancing when:

  • evidence is uncertain, stale, agent-only, or narrower than the claim;
  • the next action is commit, push, PR, merge, tag, publish, release, or handoff;
  • task/slice completion is being treated as accepted requirement satisfaction;
  • governance or retirement lacks repair/retirement evidence;
  • retained old logic lacks a retention reason and retirement trigger; or
  • complexity closure is unresolved.

Destructive or irreversible work needs scoped permission; warnings or broad assent do not grant it.

Required Evidence Slots

Keep these slots explicit and auditable:

- Evidence action / check performed:
- Result / exit status:
- Covered scope:
- Uncovered scope:
- Residual risk:
- Confidence grade: A | B | C
  • A: direct target plus relevant regression evidence; no meaningful unknown.
  • B: direct target evidence with bounded residual risk.
  • C: partial evidence only; do not claim full completion.

When tests shape the claim, include target test and related regression evidence. If automation is blocked, give reproducible manual steps and lower confidence. Evidence is not completion authority.

When a completion claim depends on an explicit baseline, artifact, owner, contract, or evidence reference, read back the smallest relevant source. For affected known references, verify a disposition: preserved, rebound to the canonical owner, retired with reason, or rejected because of conflict. Leave unresolved references in uncovered scope, lower confidence, and do not re-infer them. This readback does not prove a complete relationship graph, referential integrity, or authoritative lineage.

Task Git Closeout

For modification tasks, compare the final state with TaskStartSnapshot. Only the coordinator stages task-owned paths; never use broad staging or include pre-existing user state. A default local task commit follows fresh verification unless the task is read-only/no-change, user/project authority says no commit, or verification failed. Read back HEAD, message, files, and remaining task delta. Commit/hook failure preserves the work and blocks a clean claim; do not bypass hooks.

The Git receipt reports branch; commit SHA/message or non-commit reason; Task clean; Repository clean; and each task-created branch/worktree as created, removed, or retained with reason. Task-clean never implies repo-clean. This receipt is evidence, not external integration or completion authority.

Classify commit scope before claiming verification stability: business, process-only, mixed, or no-commit. Failed attempt telemetry is not a commit reason. A diff limited to docs/aegis/ process records does not restart already completed business-code verification; a business or test diff does.

Aegis Visibility / Single Closeout

Use one completion surface; no parallel final reports. verification-before-completion is the single completion closeout aggregator. Adjacent skills and L2 cards feed the receipt but must not replace it or become a competing final report owner. Receipt aggregation is output conformance, not a routing trigger: do not load extra skills, emit a Trace Digest, or add ceremony merely to fill the receipt.

If entry visibility was omitted, recover the decision/evidence boundary and name the gap; a used-skills list or Aegis Contribution Note is no substitute.

L0 Fast-Path

For tiny low-risk work, one natural sentence can name check/result, uncovered scope/risk, and confidence.

L1 Default Receipt

For non-trivial Aegis-shaped work, use this receipt. Evidence slots fold into Evidence strength and Uncovered risk; avoid a second evidence report.

Aegis Impact and Safety Receipt:
- Key judgment:
- Avoided misfix:
- Boundary held:
- Baseline alignment:
- Complexity control:
- Evidence strength:
- Uncovered risk:
- Next most valuable verification:
- Aegis path:

Field meanings: Key judgment=owner/root cause/requirement/completion boundary; Avoided misfix=fallback/duplicate/test accommodation/scope growth; Boundary held=contract/owner/baseline/non-goal/data/runtime boundary; Baseline alignment=aligned/Design Defect/Implementation Drift/missing-authority/needs-clarification/not triggered; Complexity control=completion-time delta/closure; Evidence strength=fresh check/result/scope/confidence; Uncovered risk=remaining gaps/residual risk; Next most valuable verification=highest-value next check; Aegis path=optional, not judgment/evidence.

Natural wording is valid when every semantic slot stays auditable. Semantic Slots, Natural Surface, and Governance Receipt are compatibility names, not other reports.

Report what was done, verified, risked, and blocked. Do not explain obvious trade-offs and do not list actions not taken; silence on unexecuted options is the compact default, n

Read the complete source ↗