Use when a branch has finished and the session-metrics card is all that is wanted — writes, commits and renders the card, and stops. The card-only half of `retro`, for sessions running close to their token budget. Where there is room to think, run `retro` instead — this one deliberately produces no findings and changes nothing.

Use when asked to review and fix an open pull request this session did not write — one another tool such as Codex opened, or another session left — and bring it to merge-ready on its own branch. Covers finding and reusing the branch's existing worktree, reading what the branch would run before running it, rebasing it and regenerating bun.lock with evidence instead of merging it, running prep-pr's review lenses on someone else's work, telling a red check main caused from one the branch caused, fixing every finding on the branch, and rewriting the body with write-pr.

Use when starting a piece of feature or fix work in this repository — taking or opening its GitHub issue, cutting the branch (a worktree on the local bare repo, an in-place branch on the remote environment) and producing the implementation plan, including the wiki pages the work will make stale and its observability plan. Also the step for turning a tracker finding into a branch without publishing it.

Use when an issue needs its complexity declared — proposing a rating from the issue body alone and getting the owner to confirm or amend it, or backfilling a rating onto an existing unrated issue. Invoked by write-issue on every issue it opens and by new-feat on an unrated issue it picks up; also the backfill path for issues opened before the label existed.

Use when composing, writing, drafting, or reviewing a PR title, PR description, or PR body in Fluid Framework — provides title style, body template, and section guidance.

Install, configure, and verify vLLM Semantic Router on a Docker host (CPU, AMD, or NVIDIA GPU) or a Kubernetes cluster, then operate it through its CLI and Router API. Use for a first install, an upgrade, routing verification, configuration changes, recipe tuning, and single-model/MoM evaluation.

Use when you help a user enable Worker tracing, configure Dashboard observability, connect an OTLP Collector to Langfuse or AgentLoop, inspect traces, or troubleshoot missing spans.

Create irresistible offers using the Value Equation, bonus stacking, risk-reversing guarantees, and ethical scarcity. Use when the user mentions "pricing strategy", "irresistible offer", "bonuses and guarantees", "value-to-price ratio", "offer naming", "grand slam offer", "guarantee strategy", or "premium pricing justification". Also trigger when packaging products for higher perceived value, designing money-back guarantees, or structuring pricing tiers to maximize conversions. Covers the MAGIC naming formula and starving-crowd targeting. For product positioning, see obviously-awesome. For outbound sales, see predictable-revenue.

Upgrade gstack to the latest version. Detects global vs vendored install, runs the upgrade, and shows what's new. Use when asked to "upgrade gstack", "update gstack", or "get latest version".

Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.

Safe, reversible database migration patterns: forward-only production changes, expand-contract zero-downtime renames, concurrent indexes, batched backfills, and per-tool workflows for PostgreSQL, Prisma, Drizzle, Kysely, Django, and golang-migrate. Use when writing a schema or data migration, adding a column or index to a large table, planning a rollback, or preparing a zero-downtime deploy.

Add a list+create page to a React app (clients/admin or clients/dashboard) — API module, page, lazy route, (admin) permission gate, Playwright test. Use when adding any frontend screen. See .agents/rules/frontend/.

Port a Retool app's functionality into a page in apps/moderator. Use when given a Retool JSON export (or asked to migrate/replace a Retool moderation tool) and a page needs to be built in the moderator app. Decodes the export, inventories its queries, and builds the page with shadcn + Tailwind under the Retool nav group.

Runs the three no-gate review lanes over everything this session touched, consolidates them, and APPLIES the fixes: comment-review (comment necessity + false claims), docs-drift-review (docs the session made wrong) and claim-review (behaviour the session's prose asserts, traced to the code). Session-scoped, not segment-scoped. Use partway through a long session, before opening a PR, and whenever a pushback has turned up an overstatement.

Reach into past AI conversation history through the `trellis mem` CLI. Use whenever the user asks 'how did we solve X last time', 'have we discussed this before', 'what was the decision on X', 'remind me what we did in this task', '上次怎么解的', '之前讨论过吗', '想起一段对话', or when starting a brainstorm that overlaps prior work, debugging a familiar bug, continuing a task across sessions, or doing a finish-work review. Returns raw past dialogue; decide for the moment whether to update spec, append to task notes, quote inline in the answer, or just internalize.

Reach into past AI conversation history through the `trellis mem` CLI. Use whenever the user asks 'how did we solve X last time', 'have we discussed this before', 'what was the decision on X', 'remind me what we did in this task', '上次怎么解的', '之前讨论过吗', '想起一段对话', or when starting a brainstorm that overlaps prior work, debugging a familiar bug, continuing a task across sessions, or doing a finish-work review. Returns raw past dialogue; decide for the moment whether to update spec, append to task notes, quote inline in the answer, or just internalize.

Reach into past AI conversation history through the `trellis mem` CLI. Use whenever the user asks 'how did we solve X last time', 'have we discussed this before', 'what was the decision on X', 'remind me what we did in this task', '上次怎么解的', '之前讨论过吗', '想起一段对话', or when starting a brainstorm that overlaps prior work, debugging a familiar bug, continuing a task across sessions, or doing a finish-work review. Returns raw past dialogue; decide for the moment whether to update spec, append to task notes, quote inline in the answer, or just internalize.

Reach into past AI conversation history through the `trellis mem` CLI. Use whenever the user asks 'how did we solve X last time', 'have we discussed this before', 'what was the decision on X', 'remind me what we did in this task', '上次怎么解的', '之前讨论过吗', '想起一段对话', or when starting a brainstorm that overlaps prior work, debugging a familiar bug, continuing a task across sessions, or doing a finish-work review. Returns raw past dialogue; decide for the moment whether to update spec, append to task notes, quote inline in the answer, or just internalize.

Test an oh-my-opencode-slim release candidate or bugfix before publishing. Use when validating a packed plugin artifact, release branch, crash fix, OpenCode runtime compatibility, or model-specific smoke test such as OpenCode 1.17.11 message transform regressions.

Create EmDash CMS plugins with sandboxed hooks, routes, storage, content and media APIs, MCP tools, and declarative admin UI, or native React and Astro extensions. Use when scaffolding or implementing an EmDash plugin.