subagent-review-cycles — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited subagent-review-cycles (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
| Role | Job |
|---|---|
| Leader (main agent) | Dispatch, integrate review results, accept / reject, communicate with the user |
| Developer (subagent) | Draft / revise document sections; works after Leader replies with rejection. (The Developer role is often dispatched as a Software Architect sub-agent type when the task is architectural in nature, but the role name remains "Developer".) |
| Code Reviewer (subagent) | Audits Developer output for technical / API correctness and logic gaps; CLI forbidden, WebSearch allowed |
The Leader never writes the implementation / drafts a section directly — that's the Developer's job. The Leader never does the review either — that's the Code Reviewer's job.
round N:
Leader → Developer: dispatch (scope + skills + inputs + return format + criteria)
Developer → Leader: draft
Leader → Code Reviewer: dispatch (review criteria + must use WebSearch, no CLI)
Code Reviewer → Leader: BLOCKER / MAJOR / MINOR list
Leader: ACCEPT / REJECT each item with explicit reason
if accepted_count == total: done
if N == limit: pause, report to user
else: round N+1 with feedbacklimit(N) is typically 3–5. If the limit is reached without convergence: pause, report to the user, wait for direction.
If a round-1 result has only spelling / formatting / paragraph order / string typo cosmetic-grade fixes left:
Criteria: the fix can be completed by the Leader in ≤ 5 minutes and involves no new decisions.
Every Code Reviewer dispatch prompt must include:
For each review finding the Leader gives:
REJECT must cite specific evidence (API doc, prior decision, design constraint); pure preference is not acceptable.
A separate close-the-loop activity that fires once per phase (not once per review round): before the Leader signs off on a phase-completion PR, run a sweep against the phase's diff scope to catch deferred-and-forgotten debt.
Command (Leader-run; against the phase's diff scope, not the full repo):
rg -n --no-heading -e 'TODO|FIXME|XXX|HACK|stub|placeholder|Phase [0-9]+ Part' <source-root>/Replace <source-root>/ with the actual source directory for this project (e.g. Packages/<target>/Sources/, Sources/, src/). The path must match the repo's layout — if it doesn't, the sweep silently finds nothing and the phase incorrectly appears clean.
Disposition rule — every match must fall into exactly one bucket; otherwise the phase is not complete:
design.md, engineering → foundations.md, implementation step → plan.md, collaboration → methodology.md), and the §Backlog entry cites the source `file:line` so the debt is traceable.Stub / placeholder code without a literal TODO comment still counts. Identifier names like xxxPlaceholder, xxxStub, or scaffolding values that are not real implementations must be flagged in the phase log even if the regex didn't catch them via comment text.
Ownership: the Leader runs the sweep. Subagents may flag debt during implementation (in their impl-notes §未決), but closing the loop before phase merge is non-delegable. A PR reviewer subagent dispatched for the phase-completion PR should also run the sweep against the diff and report findings as MAJOR (unless already documented per the disposition rule above).
When to invoke:
Anti-pattern: marking a regex match as "obviously fine, ignore" without writing the disposition down. The point of the sweep is the paper trail; an undocumented justification is indistinguishable from forgetting.
leader-developer-handoff-contract: details the 5 elements of each sub-agent dispatch.spec-phase-orchestration: review cycles are usually embedded in the spec phase.methodology-pattern-extractor: "round-1 cosmetic inline edit" is a codifiable pattern.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.