AGENTS.md · garrytan/gstack

Sections

1. Available skills
2. Validation discipline
3. Build commands
4. Platform support
5. Key conventions

First lines (shown under the repo's MIT license)

# gstack — AI Engineering Workflow

gstack is a collection of SKILL.md files that give AI agents structured roles for
software development. Each skill is a specialist: CEO reviewer, eng manager,
designer, QA lead, release engineer, debugger, and more.

## Available skills

Skills live in `.agents/skills/` (or `~/.claude/skills/gstack/` on Claude Code).
Invoke them by name (e.g., `/office-hours`).

### Plan-mode reviews

| Skill | What it does |
|-------|-------------|
| `/office-hours` | Start here. Reframes your product idea before you write code. |
| `/plan-ceo-review` | CEO-level review: find the 10-star product in the request. |
| `/plan-eng-review` | Lock architecture, data flow, edge cases, and tests. |
| `/plan-design-review` | Rate each design dimension 0-10, explain what a 10 looks like. |
| `/plan-devex-review` | DX-mode review: TTHW, magical moments, friction points, persona traces. |
| `/plan-tune` | Self-tune AskUserQuestion sensitivity per question. |
| `/autoplan` | One command runs CEO → design → DX → eng review (eng always last). |
| `/design-consultation` | Build a complete design system from scratch. |
| `/spec` | Turn vague intent into a precise, executable spec in five phases. Files a GitHub issue, optionally spawns a Claude Code agent in a fresh worktree, and lets `/ship` close the source issue on merge. |

### Implementation + review

| Skill | What it does |
|-------|-------------|
| `/review` | Pre-landing PR review. Finds bugs that pass CI but break in prod; lists every gate edit for gate integrity. |
| `/deslop-shared-libs` | Find worthwhile shared-code extractions in recent work. Recommendations only. |
| `/write-skill` | Write or improve an agent skill without bloat: edit ladder, size per level (`gstack-skill-bill`), skill-to-bin drift check, full diets with a before/after test. |
| `/test-audit` | Sweep existing tests for low-value, implementation-coupled or duplicate tests. Report-only unless you approve a batch. |
| `/codex` | Second opinion via OpenAI Codex. Review, challenge, or consult modes. Available outside the Codex harness. |
| `/claude-code` | Second opinion via Claude Code. Review, challenge, or consult modes. Available outside the Claude Code harness. |
| `/investigate` | Systematic root-cause debugging. No fixes without investigation. |
| `/design-review` | Live-site visual audit + fix loop with atomic commits. |
| `/design-shotgun` | Generate multiple AI design variants, comparison board, iterate. |
| `/design-html` | Generate production-quality Pretext-native HTML/CSS. |
| `/design-motion` | Turn an approved design into a showcase loop: MP4 for X, website GIF, 800×500 GIF, with seam, rest and overflow checks. |
| `/devex-review` | Live developer experience audit (TTHW measured against the real flow). |
| `/qa` | Test browser, API, CLI, job, worker and webhook behavior; reproduce bugs, fix them and re-verify. |
| `/qa-only` | The same surface-aware QA, reporting findings and proposed tests without changing product code or tests. |
| `/scrape` | Pull data from a web page in your Aside browser, with your real logged-in state. Read-only. On the fallback browser a codified browser-skill answers a repeat intent in ~200ms. |
| `/skillify` | Codify the most recent successful `/scrape` flow into a permanent browser-skill (fallback browser only). |

### Release + deploy

| Skill | What it does |
|-------|-------------|
| `/ship` | Run tests, review, gate integrity, push, open PR. Workspace-aware version queue. |
| `/land-and-deploy` | Merge the PR, wait for CI and deploy, verify production health. |
| `/modernize` | Bring an aging PR onto its current base and decide MODERNIZE, REWORK or CLOSE, with `git range-diff` proof before a pinned-lease push. Never closes a PR itself. |
| `/canary` | Post-deploy monitoring loop in your Aside browser (or gstack's own when Aside is absent). |
| `/landing-report` | Read-only dashboard for the workspace-aware ship queue. |
| `/document-release` | Audit relevant docs before final verification on every ship; also supports standalone documentation updates. |
| `/document-generate` | Generate Diataxis docs (tutorial / how-to / reference / explanation) from code. |
| `/setup-deploy` | One-time deploy config detection (Fly.io, Render, Vercel, etc.). |
| `/gstack-upgrade` | Update gstack to the latest version. |

### Operational + memory

| Skill | What it does |
|-------|-------------|
| `/context-save` | Save working context (git state, decisions, remaining work). |
| `/context-restore` | Resume from a saved context, even across Conductor workspaces. |
| `/learn` | Manage what gstack learned across sessions. |
| `/retro` | Weekly retro with per-person breakdowns and shipping streaks. |
| `/health` | Code quality dashboard (type checker, linter, tests, dead code). |
| `/captain` | Run a crew from one controller: READY contract, merge trains, digest, approvals shapes, daily flaky pass. Also `/crew`. Templates in `captain/templates/`, team guide in `docs/captain.md`. |
| `/benchmark` | Performance regression detection (page load, Core Web Vitals). |
| `/ubicloud` | Run a heavy suite, build or eval on an ephemeral 16-vCPU Ubicloud VM: TTL-named VMs with a reaper, quota preflight, hang watchdog, one committed verify per repository. |
| `/benchmark-models` | Cross-model benchmark for skills (Claude, GPT, Gemini side-by-side). |
| `/eval-plan` | Preregister a paid eval (bars, arms, decoys, stop rules), dry-run it for $0, pilot three priced items, then approve the spend. |
| `/cso` | Supported security findings with explicit coverage. Static assessment remains available without catalog profiles. Contained runtime and scanner execution needs Docker and a matching qualified profile. The runtime catalog qualifies ten images: Node 24.4.0, Bun 1.3.10, Python 3.13.4 with uv 0.8.0, Rails on Ruby 3.4.4, and PostgreSQL 17.2, each for linux/amd64 and linux/arm64. The scanner catalog qualifies twelve: gitleaks, OSV-Scanner, Schemathesis, Semgrep, Trivy and zizmor on both platforms. Without Docker, or where no profile matches (native Windows Docker, for example), `/cso` runs static assessment only. Runtime-tested bundles authenticate separate external assertions. Project-test completion remains `self_reported` because target code controls the test process; `tested` is reserved for a future target-independent completion witness. |
| `/setup-gbrain` | Set up gbrain for cross-machine session memory sync. |
| `/sync-gbrain` | Keep gbrain current with this repo's code; refresh agent search guidance in CLAUDE.md. |

### Browser + agent integration

Every browser skill drives the Aside AI browser first (macOS 15+, aside.com) —
the user's real browser with their real sessions, through `aside repl` scripts;
gstack never installs it. When Aside is not installed or not running (Linux,
Windows, a closed Aside app) the same skills fall back automatically to gstack's
own headless Chromium (`$B`), which is where the three skills under `/browse` apply.

| Skill | What it does |
|-------|-------------|
| `/browse` | Drive a browser: open a page, read it, click through a flow, screenshots, console errors. Aside first; gstack's own Chromium (~100ms/command) as the fallback. Every other browser skill stands on it. |
| `/open-gstack-browser` | Launch the visible GStack Browser with sidebar + stealth — the headed face of the fallback engine. |
| `/setup-browser-cookies` | Import cookies from your real browser into the fallback engine for authenticated testing. Unnecessary on Aside. |
| `/pair-agent` | Pair a remote AI agent (OpenClaw, Codex, etc.) with gstack's own browser over a scoped tunnel. |

### iOS QA — drive real iPhones over USB or Tailscale (v1.43.0.0+)

| Skill | What it does |
|-------|-------------|
| `/ios-qa` | Live-device iOS QA via USB CoreDevice tunnel + embedded StateServer. Optionally exposes the device over Tailscale so remote agents can drive it. |
| `/ios-fix` | Autonomous iOS bug fixer with regression snapshot capture. |
| `/ios-design-review` | Designer's-eye QA on a real iPhone — 10-dimension Apple HIG rubric. |
| `/ios-clean` | Convenience: strip DebugBridge + #if DEBUG wiring before a Release build. |
| `/ios-sync` | Regenerate the iOS debug bridge against the latest upstream templates. |

Companion CLIs (run on the Mac that's plugged into the device):

| Command | What it does |
|---------|-------------|
| `gstack-ios-qa-daemon` | Mac-side broker. Loopback by default; `--tailnet` adds a Tailscale-facing listener with capability tiers and audit logging. |
| `gstack-ios-qa-mint` | Owner-grant CLI for the tailnet allowlist (`grant`/`revoke`/`list`). |
| `gstack-ios-qa-regen` | Regenerate the canonical local DebugBridge package and typed accessors (`--app-source` / `--bridge-dir`). |

End-to-end walkthrough: [docs/howto-ios-testing-with-gstack.md](docs/howto-ios-testing-with-gstack.md).

### Safety + scoping

| Skill | What it does |
|-------|-------------|
| `/careful` | Warn before destructive commands (rm -rf, DROP TABLE, force-push). |
| `/freeze` | Lock edits to one directory. Hard block, not just a warning. |
| `/guard` | Activate both careful + freeze at once. |
| `/unfreeze` | Remove directory edit restrictions. |
| `/make-pdf` | Turn any markdown file into a publication-quality PDF. Renders through Aside, or gstack's own browser when Aside is absent. |
| `/diagram` | English in, diagram out: mermaid source + editable .excalidraw + SVG/PNG, offline. Renders through Aside, or gstack's own browser when Aside is absent. |

## Validation discipline

When fixing failures or preparing `/ship`, follow this order:

1. List the known failing cases, their logs and source revision, the demonstrated
   cause, and the smallest check that can prove each repair. Keep one current
   list in `.context/`; update it instead of starting overlapping repair plans.
   Reconcile the runner's failure total with named failures and unhandled or
   module-load errors; the named-test footer alone is not the complete inventory.
2. Resolve base-branch integration and assign one owner per shared file before
   editing. Keep repairs within the observed failures and the user's scope.
   Before a fixture writes through a link, resolve its target and verify it stays
   inside that fixture's temporary root; live skill registrations can point back
   into this checkout.
   When upstream replaces a helper API, inventory every direct caller, mock
   adapter, source snapshot, generated golden, and selection edge before choosing
   focused checks. Verify extracted test adapters supply the current imports and
   result schema; an adapter failure is not evidence that production failed.
   Schedule independent checks independently. Gate a check only on inputs or
   prerequisites it actually needs; an unrelated failure must not serialize the
   whole validation plan. Keep source fixed while tests live-link its files.
3. Diagnose before changing code. Distinguish a product defect, an invalid test
   expectation, a detector/fixture defect, and a launch/environment failure.
   Preserve the original failure. Do not call it pre-existing without evidence.
   Verify pinned runtime tool schemas and defaults before treating omitted fields
   as model noncompliance.
   Check that a bounded evaluation’s fixture scope and automated answers support
   its metric. Do not let the driver approve unrelated expansion, then blame the
   skill for the extra work; preserve required findings and evidence limits.
4. Reproduce with the smallest relevant test. For agent tests, reuse captured
   public events in free regressions, including negative controls, before paying
   for another agent run. Check behavior and acknowledgments; match exact prose
   only when that prose is the contract. Do not lower thresholds, increase model
   budgets, skip cases, or rejudge a failure to manufacture a pass. A
   pre-registered fixed panel is not rejudging.
   For any measured speedup, regression or eval delta, name the limiter that