harness-kit

Produce a consistently-styled, self-contained HTML report served privately over Tailscale. One house template (Silver Age comic-ops palette, dark/light toggle, and a mandatory copy-page button) so every report an agent hands the operator looks and behaves the same. Use when: "make an HTML artifact/report", "serve this over tailscale", "write up a brief/report/dashboard as a page", or any time you'd otherwise dump a long analysis into chat. Trigger: /artifact.

Shape a raw idea into something buildable. Product + technical exploration. Spec, design, critique, plan. Output is a context packet. Use when: "shape this", "write a spec", "design this feature", "plan this", "spec out", "context packet", "technical design". Trigger: /shape, /spec, /plan, /cp.

Use when an agent needs release intelligence from Landmark: version analysis, changelog synthesis, release notes, release-kit planning, GitHub Action adoption, fleet rollout, classification, or release artifact evidence. Trigger phrases: "Landmark", "release intelligence", "changelog", "release notes", "version bump", "release kit".

Harness engineering for Harness Kit primitives: skills, shared doctrine, provider roster, harness configs, gates, evals, bootstrap, and sync logic. Use for "improve the harness", "harness engineering", "bootstrap is wrong", "AGENTS.md is stale", "skill health", "skill usage", "undertriggering skill", "description tax", "eval skill", "sync primitives", "roster defaults", "preferred stack", "stack defaults", "hosting defaults", "CI defaults", "observability defaults", "release defaults", "design system defaults", "storage defaults", "agent substrate defaults", "one core many faces", "API CLI MCP SDK skill template", "factory product template", "generate repo-local skill", "bespoke skill subset", "domain agent skill". Trigger: /harness-engineering, /harness, /skill.

Dispatch-shaped code review: fan the diff out to fresh-context reviewers across diverse providers and model families, synthesize, fix blockers, re-review until clean. Use when: "review this", "code review", "is this ready to ship", "second-model review". Trigger: /code-review, /review.

Capture one compounding repo-technical learning while a solved problem is still fresh. Use when: after a bug fix, diagnosis, delivery, review, or incident reveals a reusable pattern worth adding to `docs/solutions/`. Trigger: /compound, /capture-learning, /learning.

Take one ticket or idea from raw intent to merge-ready (or shipped, when asked): context-first, docs→tests→code, live QA, refactor at three altitudes, semantic commits, diverse-provider review, adversarial pre-ship thinking. Use for "deliver this", "build this ticket", "make it merge-ready", "take this end to end". Trigger: /deliver.

Investigate, audit, triage, and fix. Systematic debugging, incident lifecycle, domain auditing, and issue logging. Feedback-loop-first protocol: reproduce or replay before root cause, pattern analysis, hypothesis test, and fix. Use for: any bug, test failure, production incident, error spikes, audit, triage, postmortem, "diagnose", "why is this broken", "debug this", "production down", "is production ok", "audit stripe", "log issues". Trigger: /diagnose.

Route Misty Step factory application capabilities. Use when choosing, auditing, integrating, or operating Canary, Powder, Landmark, Aesthetic, or Bitterblossom: production observability, incidents, health checks, error logging, backlog/work-card state, release intelligence, UI/UX system adoption, or supervised/unsupervised agent dispatch. Trigger: /factory-apps, /factory-stack.

Enumerates the peer AI agent CLIs installed on this machine (codex, pi, goose, opencode, claude, cursor-agent, grok, agy, hermes, oracle) and how to invoke each headlessly. A capability map, not a quota: useful for fresh-context adversarial review on a different model family, second opinions, competing attempts, and wide benches. Use when: "ask codex", "ask another model", "second opinion", "cross-model review", "what AI tools do I have", "other agents", "different model family", "adversarial critique from another provider". Trigger: /roster.

Use when an agent needs production observability from Canary: uptime, health checks, check-ins, incidents, error timelines, service evidence, webhook responder context, API keys, SDK integration, or agent-readable operational truth. Trigger phrases: "Canary", "production debugging", "incident", "health check", "error log", "monitor", "observability".

Use when an agent needs to adopt, verify, or generate Misty Step UI with Aesthetic: tokens, recipes, static registry, design law, page/specimen routes, or rendered-interface checks. Trigger phrases: "Aesthetic", "Misty Step design system", "design law", "tokens", "recipes", "law gate".

Operate Bitterblossom's `bb` event-plane CLI for agent workloads. Use when Codex needs to inspect or run `bb`, configure `plane.toml`, `agents/`, or `tasks/`, dispatch or audit tasks, handle runs, dead letters, recovery, parked tasks, submissions, gates, review-factory workflows, or help another repo consume Bitterblossom. Trigger phrases: "Bitterblossom", "bb", "event plane", "agent workload", "run a task", "inspect runs", "DLQ", "parked task", "submission loop", "review factory".

Use when an agent needs to inspect, claim, update, request input for, or complete work cards in a Powder instance. Powder is the self-hostable, agent-first work board: a durable card store with run sessions, activity, audit events, relations, optional proof, and human-in-loop states.

Verify the running thing works. Browser walks for web, request replay for APIs, local API emulation for supported third-party services, shell smoke for CLIs, consumer builds for libraries, tool-call replay for MCP. "Tests pass" is not QA. Use when: "run QA", "verify the feature", "test this", "check the app", "smoke test", "exploratory test", "capture evidence". Trigger: /qa.

Always-on backlog grooming. Tidy, brainstorm, interrogate, investigate, research, and simplify in a single loop. Tidy is not a mode — it happens every time. Strategic-layer work is a mega-sweep: swarm investigation, external research, critique, synthesis, and backlog shaping across product, codebase, docs, infrastructure, ops, architecture, system design, value prop, and agent readiness. Use when: "groom", "what should we build", "rethink this", "biggest opportunity", "backlog", "prioritize", "backlog session", "audit skills", "skill quality audit". Trigger: /groom, /groom audit, /backlog, /rethink, /moonshot, /scaffold.

Audit, design, and run repo-owned CI gates. Host-agnostic by default: local, GitHub Actions, Azure, or another runner should call the same repo-owned contract. Harness Kit's own gate is the Rust command `cargo run --locked -p harness-kit-checks -- check --repo .`; consumer repos keep their own native gate. Use when: "run ci", "check ci", "fix ci", "audit ci", "design CI", "host-agnostic CI", "Dagger", "is ci passing", "run the gates", "why is ci failing", "strengthen ci", "tighten ci", "ci is red", "gates failing", "feedback loop is slow", "run gates less often". Trigger: /ci, /gates.

Convene a council/thinktank: fan one question out to several DISTINCT high-quality OpenRouter model families (via opencode/pi), each carrying a different generative persona/perspective, then synthesize the divergent thinking as chair. Generative deliberation — brainstorm, explore the option space, weigh tradeoffs, decorrelated ideation, lock a contested direction. Distinct from /roster's adversarial critique bench (that finds bugs in an artifact; this generates and reframes). Use when: "convene a council", "thinktank", "council of models", "brainstorm with different models", "get diverse perspectives", "panel of AIs", "what would different experts think", "divergence pass", "ideate broadly", "stress-test this direction with other models". Trigger: /council, /thinktank.

Generate world-class, source-verified reference documentation for a codebase: a multi-agent loop that surveys the repo, plans the information architecture, writes facet-scoped pages, and adversarially verifies every claim against live source before committing markdown + HTML + diagrams to docs/. Always runs the full verify loop; scope is incremental by provenance. Use when: "document this codebase", "generate the docs", "build a codebase wiki", "write architecture docs", "onboarding docs", "documentation site", "keep the docs in sync", "world-class docs". Trigger: /document, /docs, /wiki.

Edit, audit, or rewrite prose so it sounds like a specific human wrote it, not a generic AI draft. Removes AI tells, filler, formulaic structure, fake polish, vague claims, and detector-bait phrasing while preserving truth, voice, and audience fit. Use when: "humanize this", "make this sound less AI", "remove AI slop", "de-slop this", "edit this prose", "make this sound natural", "fix the writing voice", "rewrite this copy". Trigger: /human-writing, /deslop.

Recommend the best next move from live thread and repo state. Use when: "what's next", "what next", "now what", "what should I do next", "what should we do next", "anything else to do", "where are we now, what's next", "what next in the backlog". Trigger: /next, /what-next, /now-what.

Browser-mode-only Oracle consults: bundle a prompt plus selected files and ask a signed-in ChatGPT GPT-5.5 Pro browser session for a second opinion. Use when stuck, debugging hard bugs, reviewing an architecture plan, or cross-checking a substantive diff with large file context. Never use Oracle API mode from Harness Kit. Trigger: /oracle, /consult.

Fast session-start repository orientation from live local evidence. Use when: "orient yourself", "start of session", "new session", "where are we", "catch me up before acting", after compaction, after switching worktrees, or before choosing a Harness Kit workflow. Trigger: /orient, /ground, /session-start.

Architecture refactor mode: set a concrete improvement goal, refactor until the architecture is simpler and coherent, live-test after each significant step, autoreview, commit green milestones, and track progress in /tmp/refactor-{project}.md. Use when: "refactor this", "clean up the architecture", "make the design better", "refactor until you're happy", "pay down design debt", "simplify this subsystem". Trigger: /refactor.

Web research, multi-AI delegation, and multi-perspective validation. /research [query], /research delegate [task]. Use when: "search for", "look up", "research", "delegate", "get perspectives", "web search", "find out", "investigate", "introspect", "check readwise", "saved articles", "reading list", "what are people saying", "X search", "trending", "which model", "compare models", "best model for", "model selection".

Turn a working repo into credible external-facing proof: demoability audit, deterministic demo path, marketing site, case study, screenshots, demo video, launch copy, and consulting portfolio assets. Use when: "productize this", "make this demoable", "make this polished", "make a marketing site", "show this off", "demo video", "case study", "portfolio piece", "consulting asset", "launch page", "sales demo". Trigger: /showcase, /productize, /demoability.

Prove a skill beats no-skill with a falsifiable A/B eval, or retire it. Design, generate, run, and maintain a skill-specific eval: name the one claim the skill must earn, run it skill-on vs raw same-model, grade blind with objective checks first, return a keep/adapt/cut verdict. Use when: "eval this skill", "does this skill help", "prove the skill beats no skill", "write an eval for", "benchmark a skill", "is this skill worth it", "skill A/B", "skill regression test", "generate skill evals". Trigger: /skill-eval, /eval-skill, /prove-skill.

Run lane cards on Fly Sprites: remote, isolated, scale-to-zero sandboxes for heavy or parallel agent work. Golden-checkpoint provisioning so lanes start on a ready sprite with zero setup tokens. Use when: "run this on a sprite", "remote lane", "offload to a sandbox", "dispatch to sprites", "bake a sprite", "sprite fleet", heavy/long-running/parallel sub-agent work that should not run on this machine. Trigger: /sprites, /sprite-lane.

Manage the operator's Todoist as the system of record for tasks, reminders, and follow-ups — capture, triage, complete, and organize. Agent-native via the Todoist MCP; scriptable via the `td` CLI. Use when: "add this to my todoist", "add a task", "remind me to", "capture this", "what's on my todoist", "what's due today", "what's in my inbox", "mark this done", "create a project/label", "log a follow-up". Trigger: /todoist, /task, /todo.

Create or update root VISION.md as a first-class project north-star artifact. Conversational project interrogation, repo/workspace research, competitive or exemplar scan, lifespan clarification, philosophy distillation, and wiring repo-local harness primitives to read it. Use when: "vision", "vision.md", "project vision", "north star", "what is this project", "clarify product direction", "write/update VISION.md", "project philosophy", "why does this repo exist". Trigger: /vision, /north-star.

Artifact-backed interface design: critique, polish, redesign, generate, and a repo-owned design contract. One front door over a bench of design specialists — routes to exactly one primary per role; you pick the aesthetic. Requires screenshot, URL, rendered artifact, or explicit file plus intent. Use when: "make this look better", "improve the design", "polish the UI", "critique this screen", "design pass", "art direction", "make it premium", "make it brutalist/minimalist", "deslop this", "scaffold design", "DESIGN.md", "design system", "prototype this", "show me a few options", "mock up variations", "is this accessible", docs layout, report polish, generated diagrams/images, dashboards, charts, or any product-facing visual artifact. Trigger: /design, /prototype.

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", and whenever they complain about over-engineering, bloat, boilerplate, or unnecessary dependencies.

This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.

Draft user-facing announcement and marketing copy for a feature that just shipped — an X post or thread, a changelog blurb, a LinkedIn post, an email, a blog intro, or a short demo script. Spiral-agnostic by default; voice-matched via the Spiral CLI when it is installed and authed. Use when the user says 'promote this', 'draft the announcement', 'write the launch copy', 'market this feature', 'announce this feature', 'write the release tweet', or 'ce-promote'.

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

Generate ideas via named methods from creative practice.