porada/domfiles / skills/subagent-review-flow
subagent-review-flow
VerifiedUse when preparing, performing, or coordinating an independent review through native subagents, top-level reviewer threads, or provider sessions. Own initial reviewer assignments, findings reports, disputes, corrections, follow-ups, replacement handoffs, and completion within that review. Also use when creating or maintaining reusable prompts for coordinated reviews. Exclude a main agent’s standalone review and independently supplied findings or status reports outside an active review workflow.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 647 B |
| SKILL.md | skill md | 19.3 KB |
| references/guidance-recovery.md | markdown | 1.4 KB |
| references/reviewer-continuity.md | markdown | 5.5 KB |
references/reviewer-continuity.md
View on GitHub# Reviewer Continuity
## Continue in a Fresh Session
Preserve mandated provider, model, settings, environment, and lifecycle requirements. Record the predecessor, successor, reason, and transferred obligations. Proceed under existing authority when it covers the replacement and all separate requirements are satisfied.
A new session doesn’t start a new round or reset finding identifiers, correction history, valid clearance, or execution limits. Don’t use replacement chains to evade disagreement, access restrictions, exhausted retries, or approval requirements.
Count each successor against the [recovery replacement allowance](#recover-reviewer-continuity), with two exceptions. Ordinary continuations in fresh sessions required by the host’s lifecycle are exempt when sufficient predecessor evidence is available. Retries qualifying under [Recover Infrastructure Failures](#recover-infrastructure-failures) use that separate allowance. Apply these distinctions regardless of which route led to the new session.
For an ordinary continuation, give the successor the current assignment, applicable authority, baseline, scope, changes, outstanding findings, dispositions, validation limitations, and reuse basis. Preserve the predecessor’s reasoning, objections, and resolution exchanges as evidence distinct from coordinator conclusions. Accessible conversation references may carry detailed evidence only when the successor can retrieve them. A user-clickable link alone doesn’t establish that access.
When the calling workflow requires an independent initial assessment, give only its selected prompt or neutral assignment. Collect that report before introducing predecessor findings. Then reconcile inherited standing findings through focused follow-ups using the available evidence. Their absence from the independent report doesn’t resolve them.
If the interface requires fresh sessions for follow-ups and the caller permits it, keep predecessor material separately readable and require an independent report before it is opened. When the required separation or continuation can’t be supported, report the limitation.
The successor assumes the role’s remaining obligations and must explicitly reassess inherited standing findings. A fresh session alone doesn’t require broader review than the selected scope, but preserve complete reassessment required by the caller.
## Recover Reviewer Continuity
Use the execution interface’s bounded recovery procedure for an unavailable reviewer or missing material evidence. Resume the original conversation when recovered, or use [Continue in a Fresh Session](#continue-in-a-fresh-session) when permitted.
Classify verified transient infrastructure failures under [Recover Infrastructure Failures](#recover-infrastructure-failures). For lost assessment context or other reviewer unavailability, allow at most one recovery replacement per reviewer role in a review round, including its [early follow-ups](../SKILL.md#consolidate-each-round). Apply the counting rule in [Continue in a Fresh Session](#continue-in-a-fresh-session) to every successor.
When the initial assessment is unfinished or evidence can’t support a continuation, require a permitted replacement to assess the complete current scope independently before reconciling available predecessor findings and objections. Record remaining evidence gaps and the obligations they prevent the successor from resolving.
If the permitted replacement can’t complete its assessment after bounded recovery, use the limited-review endpoint rather than starting another replacement. Ask only when the user has necessary information or authority, or must make a material decision.
### Recover Infrastructure Failures
Use this route only when host evidence identifies a transient execution or transport failure and establishes either that assessment never began or that the complete assessment context remains retrievable for continuation. Missing output, a timeout, or a matching session identifier alone doesn’t establish either condition. Missing material context uses the recovery replacement rule above. If execution state is uncertain, establish safe continuation or termination through the host before retrying or replacing the reviewer.
Allow at most two infrastructure retries per reviewer role in a review round, shared across initial execution, replacements, and early follow-ups. Count each reattempt of a failed operation, whether it resumes a session or creates a permitted successor. Keep this count separate from the recovery replacement count in the existing review record. Preserve stricter host, caller, retry, and timeout limits. Neither successful recovery nor changing sessions or interfaces resets the counts within that round. Exhaustion of either allowance cannot be evaded by reclassifying the same failure under the other route.
Before retrying, establish that the earlier operation has ended or can be safely resumed without duplicate assessment. Retain all available findings, objections, dispositions, and validation evidence, and transfer them under [Continue in a Fresh Session](#continue-in-a-fresh-session) when needed. Preserve the selected provider, model, settings, environment, and disclosure authority. An access denial, unavailable required capability, assessment disagreement, or exhausted limit doesn’t qualify as a transient infrastructure failure.
When bounded recovery cannot restore the required assessment, use the limited-review endpoint with the standing findings and evidence gaps intact. Infrastructure recovery supplies no clearance of its own.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |