From aegis
Enforces running verification commands and confirming output before claiming work complete, fixed, or passing—prior to commits, PRs, or success assertions. Includes QA closure steps and confidence grading.
npx claudepluginhub ganyuanran/aegis --plugin aegisThis skill uses the workspace's default tool permissions.
→ About to claim "done", "passing", "fixed", "complete"? → **Run the verification command first. Then claim.**
Enforces running verification commands (tests, linter, build) and confirming output before claiming work complete, fixed, or passing—before commits/PRs.
Enforces evidence-based verification by running fresh tests, builds, linters, reviewing outputs before claiming work done, committing, or PRing.
Enforces running verification commands like tests, linters, and builds before claiming work is complete, fixed, or passing, especially prior to commits or PRs.
Share bugs, ideas, or general feedback.
→ About to claim "done", "passing", "fixed", "complete"? → Run the verification command first. Then claim.
Claiming work is complete without verification is dishonesty, not efficiency. Evidence before claims, always.
Before ANY success/completion claim, expression of satisfaction, commit, PR, task completion, or delegation. Applies to exact phrases, paraphrases, and implications.
Remove/Restore: side effects? temp instrumentation restored?
Evidence Bundle: exact command, scope, exit status, key output. State what's covered and what's not. Include target test and related regression evidence. When automation is blocked, provide reproducible manual verification steps.
Prompt Hygiene: when external output shaped judgment → state whether summaries or raw excerpts were used. Name large payloads not loaded. If summary insufficient → read back excerpt or lower claim. Include Evidence Used / Not Loaded / Next Evidence boundary when relevant.
Confidence: A (direct + regression, no unknowns) | B (direct, bounded risk) | C (partial only, not closed)
Authority: verified evidence ≠ authoritative completion. Keep distinct.
Long-Task: re-read checkpoint, confirm every todo has status, no drift check unresolved.
Workspace Integrity: if the task created or modified a target project's
docs/aegis/ workspace and scripts/aegis-workspace.py is available, run
python scripts/aegis-workspace.py bundle --root <target-project-root> --work YYYY-MM-DD-<slug>
when a work/ record exists, then run
python scripts/aegis-workspace.py check --root <target-project-root> and
include the result in the evidence bundle. The generated proof bundle and
workspace check validate method-pack structure, index coverage, and
recognizable JSON artifact sidecars only; they do not judge evidence
sufficiency and do not grant completion authority.
Governance Closure: for governance/cleanup/migration/compatibility/retirement work → final response must include. Do not skip this structure just because the implementation was small. Localize section labels and prose to the user's language; keep internal concepts in English only when they are product terms or file/path identifiers.
Repair Track: repaired object | action | impact | verification
Retirement Track: retired object | action | retained boundary | future trigger
Residual Risk: unverified | deferred