Guide multi-round plan reviews with exit criteria and severity tracking.
npx skills add https://github.com/tetran/Hotwire-ToDo --skill plan-review-loop
Please help me install this Agent Skill. Skill: plan-review-loop Source: https://github.com/tetran/Hotwire-ToDo/tree/main/.claude/skills/plan-review-loop Command: npx skills add https://github.com/tetran/Hotwire-ToDo --skill plan-review-loop
Hobo-specific operational playbook for the P3 Plan Review Loop — how to draft a plan that survives review, how to scaffold revision-prompts so round 2 is a verification pass instead of a re-read, when to STOP looping (severity trajectory + actionable-vs-zero exit), what plan-reviewer is structurally blind to (orthogonal axes, runtime collisions), and the same iterative pattern applied to codex review of prescriptive process docs. Load BEFORE invoking the plan-reviewer subagent in P3, BEFORE submitting a v2/v3 revision after addressing prior findings, BEFORE deciding whether a "no high-severity" round means done, and BEFORE running codex review --base main against changes to docs/process/, .claude/agents/, .claude/skills/, or any prescriptive workflow doc. Also load when the user says "plan-reviewer", "プランレビュー", "Plan Review Loop", "P3 のレビュー", "review loop", "何ラウンド回せばいい？", "もう収束した？", "actionable findings", or asks why plan-reviewer keeps surfacing new findings each round.
The skill provides a repeatable, round-based protocol for plan reviews, including load-time pre-checks to ensure audience alignment; a convergence model based on actionable findings; scaffolding prompts to speed round-2 revisions; clear exit criteria when no actionable findings remain; and guidance on handling orthogonal runtime concerns to avoid blind spots.
Load this playbook before starting a plan review to scaffold round-2 prompts and accelerate convergence.
High-intent search queries and answers about installing and using this skill.
A multi-round plan review converges when severity trajectories show zero actionable findings remain. Use round-based exit criteria to verify the plan is safe rather than re-reading unchanged sections endlessly.
New findings appear each round when revision prompts lack scaffolding. Use structured convergence frameworks to scaffold round-2 prompts as verification passes, preventing orthogonal runtime concerns from emerging late.
Scaffold revision prompts by framing round 2 as a verification pass against prior findings rather than a full re-read. This repeatable framework accelerates convergence by tracking severity trajectories and actionable items.
Yes, the plan review loop pattern applies to codex review of prescriptive process docs. It enforces round-based exit criteria and records severity trajectories to prevent rollout blind spots in workflow documentation.
Orthogonal runtime concerns are blind spots a plan reviewer is structurally blind to, such as runtime collisions. Surface these axes explicitly during the loop to prevent rollout blind spots before finalizing the plan.
Manage convergence by enforcing round-based exit criteria based on actionable findings. A repeatable loop framework records severity trajectories and surfaces orthogonal runtime concerns to prevent rollout blind spots.
endearqbGuides a six-question diagnostic flow to draft a design doc.
joekhosbayarIdentify alignment gaps between GDD, UX, and Epics for production rollout.
troykellyExecute a code-reviewer subagent to analyze code quality and standards adherence.
HmbownAdd observability, logging, and runbooks to systems lacking visibility.
