Live decision-review session between graveyard shifts. Compile every decision and approval currently waiting on the user — across ALL prior shifts, not just the latest — walk them together, and RECORD each outcome onto GitHub as shaped permission rather than executing it live (execution is the graveyard's job; building/merging mid-meeting just makes the user wait). Reactions are cues to capture; even approvals are deferred to the next graveyard. End by publishing the report and — with standing permission — launching that graveyard shift.
Adversarially review a graveyard shift's brief BEFORE it's published — kill false gates, sharpen real ones, surface actionable work the shift left behind, and loop the graveyard if real work remains. Use as the closing/looping phase of graveyard-shift, right after the Shift Report is drafted and before it's published to Notion. This is what makes a graveyard shift loop until review finds no actionable-now work remaining; it is NOT run during a shift-change (that's a live meeting with the user and can't loop).
Work through the open issue backlog autonomously. Auto-ship the small clean fixes, prep draft PRs for review on bigger ones, file refined proposals when design choices need user input. For unattended sessions where the user is sleeping / away and wants to wake up to a productive set of changes.
The definition-of-done gate. Run before declaring any unit of work done or finished — before merging an auto-ship, handing back a draft PR, closing an issue, or listing an item as "shipped" in a shift report. Nine ownership questions plus a short close-out posted on the PR/issue. Any unanswerable question flips the item to a lesser bucket instead of shipping a hole.
Review a plan, issue, spec, PR, current diff, or implementation against an authoritative source of truth; identify missing, incorrect, risky, overcomplicated, or unverifiable work; patch clear gaps when requested; optionally run an advisory external reviewer (e.g. the codex-pr review loop / codex/AGY) for implementation diffs.
Use when urgency matters and the right move is a direct, root-cause fix instead of cautious layering.
Review code, prompts, validators, regexes, heuristics, fallback logic, shell/wrapper authority, over-specific field ownership, and duality (two paths for two callers) for brittle patching or overengineering that masks product intent. Use when a function or feature may be over-controlled with deterministic regexes, fallback piles, quality gates, compatibility branches, large schemas, producer shells that carry creative/continuity authority, premature per-field authoring, detailed upstream contracts, or two parallel implementations of the same logical step that must stay in sync.
Audit LLM prompt strings (system prompts, instruction templates, tool descriptions, agent instructions) along two axes — Direction (positive vs. negative phrasing) and Prescriptiveness (directorial framing vs. enumerated palette / choose-from list) — and propose reframings that shape how the LLM thinks rather than what it must choose. Use when reviewing prompt files, when prompts have grown long with prohibition lists or option taxonomies, when prompt shells may override committed section prompts or final authored artifacts, when output is brittle (LLM ignores rules, defaults to safe bland choices, or cycles through a checklist), or when adding/refactoring prompt instructions. Recognizes legitimate enumeration cases (validated enums, provider-required values, safety/refusal contexts, image-gen negative_prompt input, legal exclusions) and skips them with a note.