dzhng

Audit the decisions an implementing agent made, not its diff — a pure audit that traces the session's history into a decisions ledger, changes no code, and never blocks an unsupervised run. Working code still embeds architecture the user never chose; surface…

Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's…

Implement an existing spec through committed passes. Use for long or multi-pass specs that need maintenance checkpoints to periodically clean code, handoffs, priorities, and plan bloat before drift accumulates.

Break large features into independently verifiable, human-reviewable slices under a feature directory in specs/. Use for risky or multi-step feature work that needs upfront questioning, API seams, browser-playable checkpoints, HTML visualizations, screenshot…

Audit or rewrite AGENTS.md so it holds only lasting principles. Run it only when the user asks for it by name; never invoke it on your own.

Review changed code for naming, stale references, unnecessary complexity, and comment quality. Use after completing implementation work, before committing, or when the user asks to review or audit code.

Write tests that pin real behavior instead of implementation details, config values, or lucky samples. Use when adding tests for new behavior, writing a regression test, fixing a brittle or flaky test, reviewing a test diff, or when a test breaks after a…

Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a second opinion after completing a substantive change, before presenting it as done or committing; (2) delegate a well-defined implementation task…

Review changed code for naming, stale references, unnecessary complexity, and comment quality. Use after completing implementation work, before committing, or when the user asks to review or audit code. Enforces at review time the authoring rules of…

How to write and iterate on tests in this repo — one test at a time (tracer bullets), fast cargo first, scale 1v1 before armies, control variables, measure mechanisms not noise. Use when adding sim behavior, fixing a red or brittle test, reviewing a test…

Architecture rules for GPU rendering with TypeGPU/WebGPU. Use when adding or changing render passes, shaders, frame orchestration, GPU resources, culling, terrain, shadows, or visual performance work.

Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or…

Use the unprimed sub agent as a second set of eyes before accepting visual work — MANDATORY before declaring any user-reported visual bug fixed or claiming a visual change verified; primed eyes pass defects fresh eyes catch.

Implement an existing spec through committed passes. Use for long or multi-pass specs that need maintenance checkpoints to periodically clean code, handoffs, priorities, and plan bloat before drift accumulates.

Break large features into independently verifiable, human-reviewable slices under a feature directory in specs/. Use for risky or multi-step feature work that needs upfront questioning, API seams, browser-playable checkpoints, HTML visualizations, screenshot…

Use when writing or reviewing geometry, simulation, collision, navigation, culling, procedural generation, transforms, or other performance-sensitive algorithms with the npm `math` package, or when the user invokes /math. Not for routine arithmetic or…

Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a second opinion after completing a substantive change, before presenting it as done or committing; (2) delegate a well-defined implementation task…

Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or…

Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's…

Implement an existing spec through committed passes. Use for long or multi-pass specs that need maintenance checkpoints to periodically clean code, handoffs, priorities, and plan bloat before drift accumulates.

Use the unprimed sub agent as a second set of eyes before accepting visual work — MANDATORY before declaring any user-reported visual bug fixed or claiming a visual change verified; primed eyes pass defects fresh eyes catch.

Break large features into independently verifiable, human-reviewable slices under a feature directory in specs/. Use for risky or multi-step feature work that needs upfront questioning, API seams, browser-playable checkpoints, HTML visualizations, screenshot…

Write tests that pin real behavior instead of implementation details, config values, or lucky samples. Use when adding tests for new behavior, writing a regression test, fixing a brittle or flaky test, reviewing a test diff, or when a test breaks after a…

Audit the choices an implementing agent made, not its diff — a pure decision audit that traces the session's history into a choices ledger, changes no code, and never blocks an unsupervised run. Working code still embeds architecture the user never chose;…

Architecture rules for GPU rendering with TypeGPU/WebGPU. Use when adding or changing render passes, shaders, frame orchestration, GPU resources, culling, terrain, shadows, or visual performance work.

Implement an existing spec through committed passes. Use for long or multi-pass specs that need maintenance checkpoints to periodically clean code, handoffs, priorities, and plan bloat before drift accumulates.

Break large features into independently verifiable, human-reviewable slices under a feature directory in specs/. Use for risky or multi-step feature work that needs upfront questioning, API seams, browser-playable checkpoints, HTML visualizations, screenshot…

Ratchet source file size so every file stays small enough for an agent to read whole: find every file over a token budget, split oversized files by concept, and set up the pre-commit ratchet that stops them from growing. Use when a commit is blocked because a…

Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a second opinion after completing a substantive change, before presenting it as done or committing; (2) delegate a well-defined implementation task…

Generate Ian-style Xiaohei illustrations for articles, posts, blogs, Notion documents, workflows, methods, processes, structures, states, metaphors, and opinions. Use when the user asks for weird, hand-drawn, Xiaohei, article, editorial, body illustrations,…

Shoot software UI like a film. A sequence of hero shots, each a steep, oblique, extreme close-up of the interface floating in black, with a razor-thin focal plane, a slow motivated camera drift, and UI that acts on its own, hard-cut on the action, ending on…

Build animations and interactive elements (explainers, figures, hero visuals, step-through walkthroughs) in the crafted isometric "Anatomy" style, with many small precise solid parts, four-tone shading, correct painter's order, a framed card with title, hint…

Create or revise agent skills. Use when adding a new skill file, renaming a skill, simplifying an existing skill, improving trigger descriptions, or deciding what belongs in a skill versus references, scripts, assets, or ordinary docs.

Audit or rewrite AGENTS.md so it holds only lasting principles. Run it only when the user asks for it by name; never invoke it on your own.

Write a live eval for new or changed runner/agent behavior using red/green TDD plus a falsification check that proves the eval fails when the behavior is broken. Use whenever you add or modify behavior that should be covered by an eval, when asked to "write…

Refactor cleanly instead of layering sediment. Use for rename requests, stale or misleading names, changed scope, or when a change reveals duplicated concepts, local adapters, obsolete owners, redundant inputs or guards, compatibility wrappers, parallel…

Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a second opinion after completing a substantive change, before presenting it as done or committing; (2) delegate a well-defined implementation task…

Reproduce observational-memory bugs (reflection, recall, observer, freshness, eviction) by dumping the live `~/.duet/memory.db` into a fixture and driving an eval against it. Use whenever the agent's memory misbehaves — wrong observations, bad reflections,…

Increment the package version, commit the release, create a matching version tag, and push main plus the tag. Use when releasing this repo, publishing the package, bumping the version, tagging a release, or when the user asks to "release", "bump ver", "tag",…

Review changed code for naming, stale references, unnecessary complexity, and comment quality. Use after completing implementation work, before committing, or when the user asks to review or audit code.

Manage contacts, companies, deals, and pipeline with crm.cli — a headless CLI-first CRM backed by SQLite with a virtual filesystem interface

Generate Ian-style Xiaohei illustrations for articles, posts, blogs, Notion documents, workflows, methods, processes, structures, states, metaphors, and opinions. Use when the user asks for weird, hand-drawn, Xiaohei, article, editorial, body illustrations,…