Skip to content

notque/vexjoy-agent / skills/game/game-dev

game-dev

Flagged

Game development: design, asset pipelines, Phaser, Unity CLI and builds, vanilla JS frontend, GM mode, match booking.

FileKindSize
SKILL.mdskill md14.7 KB
references/anchor-alignment.mdmarkdown16.0 KB
references/animate-scaffolds.mdmarkdown2.0 KB
references/arcade-physics.mdmarkdown7.4 KB
references/artifacts-and-prototyping.mdmarkdown1.5 KB
references/asset-sources.mdmarkdown7.9 KB
references/audit-and-red-team.mdmarkdown795 B
references/autonomous-improvement.mdmarkdown10.3 KB
references/backend-chain.mdmarkdown10.4 KB
references/bg-removal-local.mdmarkdown22.7 KB
references/build-scaffolds.mdmarkdown2.0 KB
references/capabilities/01-design-red-team-audit.mdmarkdown3.9 KB
references/capabilities/02-emotional-canvas-moodboard.mdmarkdown3.7 KB
references/capabilities/03-game-design-attribution-audit.mdmarkdown3.6 KB
references/capabilities/04-game-design-bartle-archetype-audit.mdmarkdown3.7 KB
references/capabilities/05-game-design-big-five-personality-audit.mdmarkdown3.6 KB
references/capabilities/06-game-design-brainstorm-methods.mdmarkdown3.9 KB
references/capabilities/07-game-design-core-loop-extractor.mdmarkdown3.7 KB
references/capabilities/08-game-design-craft-critique.mdmarkdown3.5 KB
references/capabilities/09-game-design-creative-unblocker.mdmarkdown3.5 KB
references/capabilities/10-game-design-design-pillars-extractor.mdmarkdown3.5 KB
references/capabilities/11-game-design-emotional-canvas.mdmarkdown3.6 KB
references/capabilities/12-game-design-failure-loop-audit.mdmarkdown3.8 KB
references/capabilities/13-game-design-fairness-frustration-audit.mdmarkdown3.6 KB
references/capabilities/14-game-design-fantasy-extractor.mdmarkdown3.6 KB
references/capabilities/15-game-design-feature-prioritization.mdmarkdown3.6 KB
references/capabilities/16-game-design-five-options.mdmarkdown3.5 KB
references/capabilities/17-game-design-flow-audit.mdmarkdown3.6 KB
references/capabilities/18-game-design-fogg-behavior-audit.mdmarkdown3.6 KB
references/capabilities/19-game-design-friction-journey-audit.mdmarkdown3.8 KB
references/capabilities/20-game-design-ftue-hero-journey-audit.mdmarkdown3.7 KB
references/capabilities/21-game-design-goal-density-and-immediacy-audit.mdmarkdown3.5 KB
references/capabilities/22-game-design-goal-framing.mdmarkdown3.5 KB
references/capabilities/23-game-design-granular-player-motivation-audit.mdmarkdown4.0 KB
references/capabilities/24-game-design-grow-design.mdmarkdown3.5 KB
references/capabilities/25-game-design-ideal-outcome-backcasting.mdmarkdown3.4 KB
references/capabilities/26-game-design-kpi-coverage-audit.mdmarkdown3.8 KB
references/capabilities/27-game-design-leaderboard-audit.mdmarkdown3.9 KB
references/capabilities/28-game-design-leaderboard-builder.mdmarkdown3.8 KB
references/capabilities/29-game-design-molyneux-lens.mdmarkdown3.5 KB
references/capabilities/30-game-design-multiplayer-feature-audit.mdmarkdown3.8 KB
references/capabilities/31-game-design-novelty-spectrum-audit.mdmarkdown3.6 KB
references/capabilities/32-game-design-one-page-design-doc.mdmarkdown3.8 KB
references/capabilities/33-game-design-one-thing-to-remove.mdmarkdown3.6 KB
references/capabilities/34-game-design-option-generation.mdmarkdown3.5 KB
references/capabilities/35-game-design-peak-end-audit.mdmarkdown3.6 KB
references/capabilities/36-game-design-perceived-randomness-audit.mdmarkdown3.7 KB
references/capabilities/37-game-design-pitch-deck-audit.mdmarkdown3.8 KB
references/capabilities/38-game-design-player-motivation-audit.mdmarkdown3.5 KB
references/capabilities/39-game-design-player-need-satisfaction-audit.mdmarkdown3.6 KB
references/capabilities/40-game-design-player-persona-extractor.mdmarkdown4.2 KB
references/capabilities/41-game-design-player-perspective-reframe.mdmarkdown3.7 KB
references/capabilities/42-game-design-player-segment-perception-audit.mdmarkdown3.6 KB
references/capabilities/43-game-design-player-values-mapper.mdmarkdown3.8 KB
references/capabilities/44-game-design-premium-pass-audit.mdmarkdown3.8 KB
references/capabilities/45-game-design-prosocial-session-chapters.mdmarkdown3.7 KB
references/capabilities/46-game-design-prototype-intent-audit.mdmarkdown3.7 KB
references/capabilities/47-game-design-prototyping-companion.mdmarkdown3.6 KB
references/capabilities/48-game-design-roadblock-reframing.mdmarkdown3.5 KB
references/capabilities/49-game-design-smart-goal-audit.mdmarkdown3.6 KB
references/capabilities/50-game-design-social-satisfaction-matrix.mdmarkdown3.7 KB
references/capabilities/51-game-design-systematizing-empathizing-audit.mdmarkdown3.6 KB
references/capabilities/52-game-design-thinking-fast-and-slow-audit.mdmarkdown3.6 KB
references/capabilities/53-game-design-transformative-reuse.mdmarkdown3.6 KB
references/capabilities/54-game-design-unknown-unknowns-prototyping.mdmarkdown3.6 KB
references/capabilities/55-game-design-zeigarnik-effect-audit.mdmarkdown3.6 KB
references/capabilities/56-game-dev-budget-estimator.mdmarkdown3.8 KB
references/capabilities/57-game-dev-first-steps.mdmarkdown3.6 KB
references/capabilities/58-game-dev-team-gap.mdmarkdown3.6 KB
references/capabilities/59-game-dev-time-estimator.mdmarkdown3.8 KB
references/capabilities/60-moodboard-generator.mdmarkdown4.0 KB
references/capabilities/61-software-team-conflict-patterns.mdmarkdown3.8 KB
references/capability-catalog.mdmarkdown18.4 KB
references/capability-map.mdmarkdown1.7 KB
references/capability-matrix.mdmarkdown12.5 KB
references/capacitor-ios.mdmarkdown7.3 KB
references/cognition-and-choice.mdmarkdown1.2 KB
references/cognitive-and-behavioral-lenses.mdmarkdown1.2 KB
references/combat-effects-upgrade.mdmarkdown13.3 KB
references/combat-effects-upgrade/css-3d-card-transforms.mdmarkdown10.1 KB
references/combat-effects-upgrade/css-particle-migration.mdmarkdown13.3 KB
references/combat-effects-upgrade/framer-motion-combat-juice.mdmarkdown11.9 KB
references/concept-and-loop.mdmarkdown1.5 KB
references/core-loop-and-pillars.mdmarkdown835 B
references/core-patterns.mdmarkdown8.2 KB
references/cpu-systems-harmony.mdmarkdown3.4 KB
references/creative-and-options.mdmarkdown2.0 KB
references/creative-direction.mdmarkdown1.3 KB
references/deploy.mdmarkdown5.3 KB
references/design-artifacts.mdmarkdown1.0 KB
references/emotion-and-presentation.mdmarkdown1.1 KB
references/error-catalog.mdmarkdown22.6 KB
references/fairness-and-failure.mdmarkdown1.2 KB
references/fairness-and-learning.mdmarkdown1.3 KB
references/fal-ai-image.mdmarkdown7.1 KB
references/frame-detection.mdmarkdown20.0 KB
references/full-diagnostic.mdmarkdown4.2 KB
references/game-asset-generator.mdmarkdown9.5 KB
references/game-audio.mdmarkdown7.5 KB
references/game-feel-patterns.mdmarkdown12.2 KB
references/game-pipeline.mdmarkdown11.5 KB
references/game-qa.mdmarkdown6.7 KB
references/game-sprite-pipeline.mdmarkdown33.4 KB
references/gm-brilliant-implementation.mdmarkdown13.4 KB
references/grid-shapes.mdmarkdown8.0 KB
references/meshyai.mdmarkdown7.3 KB
references/motion-pipeline.mdmarkdown7.6 KB
references/output-formats.mdmarkdown9.4 KB
references/pacing-and-return.mdmarkdown1.6 KB
references/performance.mdmarkdown7.8 KB
references/phaser-gamedev.mdmarkdown7.5 KB
references/pipeline-spec.jsonconfig23.5 KB
references/pixel-art-sprites.mdmarkdown8.7 KB
references/pixijs-combat-renderer.mdmarkdown12.1 KB
references/pixijs-combat-renderer/combat-visual-effects.mdmarkdown7.8 KB
references/pixijs-combat-renderer/pixi-2d-lighting.mdmarkdown6.6 KB
references/pixijs-combat-renderer/pixi-particle-systems.mdmarkdown9.2 KB
references/pixijs-combat-renderer/pixi-performance.mdmarkdown4.8 KB
references/pixijs-combat-renderer/pixi-post-processing.mdmarkdown6.3 KB
references/pixijs-combat-renderer/pixi-react-integration.mdmarkdown5.2 KB
references/planning-and-communication.mdmarkdown1.6 KB
references/planning-and-production.mdmarkdown1.8 KB
references/player-and-social.mdmarkdown2.3 KB
references/polish-scaffolds.mdmarkdown1.9 KB
references/progression-and-economy.mdmarkdown1.0 KB
references/promo-video.mdmarkdown6.6 KB
references/prompt-rules.mdmarkdown15.2 KB
references/quality-gates.mdmarkdown6.4 KB
references/rive-skeletal-animator.mdmarkdown7.6 KB
references/rive-skeletal-animator/rive-animation-library.mdmarkdown8.1 KB
references/rive-skeletal-animator/rive-async-patterns.mdmarkdown5.6 KB
references/rive-skeletal-animator/rive-character-pipeline.mdmarkdown5.6 KB
references/rive-skeletal-animator/rive-performance.mdmarkdown5.4 KB
references/rive-skeletal-animator/rive-react-setup.mdmarkdown9.9 KB
references/rive-skeletal-animator/rive-vs-spine-decision.mdmarkdown6.0 KB
references/road-to-aew-integration.mdmarkdown7.8 KB
references/social-and-competitive-design.mdmarkdown1.1 KB
references/social-and-competitive.mdmarkdown1.5 KB
references/spritesheets.mdmarkdown6.2 KB
references/stage-contracts.mdmarkdown11.1 KB
references/style-presets.mdmarkdown5.1 KB
references/subagent-delegation.mdmarkdown2.2 KB
references/tilemaps-and-physics.mdmarkdown13.6 KB
references/tilemaps.mdmarkdown7.0 KB
references/unity-batchmode-builds.mdmarkdown9.2 KB
references/unity-cli.mdmarkdown10.9 KB
references/unity-licensing.mdmarkdown5.0 KB
references/vfx-containment.mdmarkdown3.1 KB
references/workflow-dag.mdmarkdown4.1 KB
references/worldlabs.mdmarkdown7.9 KB
references/wrestler-archetypes.mdmarkdown7.2 KB
scripts/deterministic_idle.pyscript7.8 KB
scripts/fal_queue_image_run.pyscript9.4 KB
scripts/imgdiff.pyscript5.0 KB
scripts/meshy-generate.mjsscript11.1 KB
scripts/optimize-glb.mjsscript3.8 KB
scripts/portrait_pipeline.pyscript31.2 KB
scripts/qa_artifacts.pyscript14.4 KB
scripts/road_to_aew_integration.pyscript6.6 KB
scripts/row_job_status.pyscript8.6 KB
scripts/sprite_anchor.pyscript30.1 KB
scripts/sprite_assemble.pyscript16.0 KB
scripts/sprite_bg.pyscript28.5 KB
scripts/sprite_canvas.pyscript11.9 KB
scripts/sprite_generate.pyscript13.9 KB
scripts/sprite_pipeline.pyscript54.9 KB
scripts/sprite_process.pyscript13.5 KB
scripts/sprite_prompt.pyscript41.8 KB
scripts/sprite_slicing.pyscript38.7 KB
scripts/sprite_verify.pyscript58.5 KB
scripts/test_content_aware_extraction.pyscript13.4 KB
scripts/test_no_status_laundering.pyscript6.9 KB
scripts/test_phases_4_5_7_8.pyscript16.4 KB
scripts/test_pipeline_glue.pyscript20.9 KB
scripts/test_pipeline_patterns.pyscript10.9 KB
scripts/test_rc3_frames_distinct_threshold.pyscript14.2 KB
scripts/test_rc4_mass_centroid_default.pyscript8.3 KB
scripts/test_rc5_despill_pre_upscale.pyscript7.9 KB
scripts/test_slice_grid_cells.pyscript6.4 KB
scripts/test_slicer_strict_pitch_default.pyscript11.6 KB
scripts/test_verifier_cell_parity.pyscript9.0 KB
scripts/test_verify_gates.pyscript23.2 KB
scripts/tests/test_fal_queue_image_run.pyscript908 B
scripts/video_extract_frames.pyscript4.3 KB
scripts/video_process_frames.pyscript7.6 KB
scripts/video_select_frames.pyscript6.4 KB
scripts/with_server.pyscript5.8 KB

references/backend-chain.md

View on GitHub
# Codex CLI default with Nano Banana fallback

Operational documentation for the backend chain locked in by ADR-198. Two-step backend selection: Codex CLI first (user's existing paid subscription), Gemini Nano Banana fallback (user's existing API key), fail-loud on absence. Both paths use keys the user already holds — there is no third-party billing the toolkit hides. The Local-First principle (PHILOSOPHY.md, user-owned-key clause) authorizes this fallback chain.

## Detection logic

`sprite_generate.py` runs this in order on every generation call:

```python
def select_backend() -> Literal["codex", "nano-banana"]:
    # Step 1: Codex CLI
    if shutil.which("codex"):
        try:
            subprocess.run(["codex", "--version"], check=True, capture_output=True, timeout=10)
            return "codex"
        except (subprocess.CalledProcessError, subprocess.TimeoutExpired, OSError):
            print("[backend] codex CLI present but auth check failed; trying Nano Banana", file=sys.stderr)

    # Step 2: Nano Banana via GEMINI_API_KEY (or GOOGLE_API_KEY)
    if os.environ.get("GEMINI_API_KEY") or os.environ.get("GOOGLE_API_KEY"):
        return "nano-banana"

    # Step 3: fail loudly with both fix paths
    raise BackendUnavailableError(
        "No image-generation backend available.\n\n"
        "Fix path 1 (Codex CLI, recommended):\n"
        "  Install Codex CLI and run `codex auth` to authenticate against your existing subscription.\n\n"
        "Fix path 2 (Nano Banana fallback):\n"
        "  Set GEMINI_API_KEY (or GOOGLE_API_KEY) in your environment to enable the Nano Banana fallback."
    )
```

The error message lists BOTH fix paths so the user knows which key/install they need. Surfacing both surfaces is intentional — the user picks whichever is convenient.

## Codex CLI invocation contract (v0.125+)

ADR-198 locked in this contract. Codex CLI 0.125+ does NOT expose `--output-image`, `--aspect-ratio`, `--reference`, or `--seed` as direct CLI flags. Image generation happens through the agent's internal `image_gen` tool, invoked from prompt text.

**Command shape:**

```bash
codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check \
  [-i <ref1> <ref2> ... --] \
  "<wrapped prompt>"
```

**Wrapped-prompt semantics:**

- Aspect ratio, seed, and reference-image semantics are encoded INTO the wrapped prompt text, not as CLI flags.
- The wrapped prompt instructs the agent: `"Use your image_gen tool to create the following image. Then save the resulting PNG to this absolute path: <output>. After saving, run ls -la <path> to verify the file exists."`
- Reference images use `-i` (alias `--image`), `nargs=*`. The reference list MUST be terminated with `--` before the positional prompt — otherwise the prompt string is consumed as another image filename.
- `reference` accepts either a single `Path` or a list of `Path`s. The sprite pipeline passes a list when both a grid-canvas template and a character portrait are inputs.

**Subprocess and verification:**

- Subprocess timeout: **360 seconds**. The agent loop wrapping `image_gen` is slower than the old direct-imagegen call (the v0.124 path was ~180s; v0.125 needs the larger budget).
- Verify on success: `output.exists() and output.stat().st_size > 0`. A 0-exit with missing/empty output is treated as failure.
- The implementation lives in `scripts/sprite_generate.py:codex_generate` (HEAD commit `0178861`).

When Codex CLI evolves its image-generation surface again, this section needs an explicit revision — probably a new ADR superseding ADR-198's invocation-contract subsection. The contract is documented in this one canonical place so the next CLI revision has a clear amend target.

## Nano Banana fallback dispatch

When Codex is unavailable AND `GEMINI_API_KEY` (or `GOOGLE_API_KEY`) is set, dispatch through the existing `nano-banana-builder` skill's scripts. The skill never imports the Gemini SDK directly — composition through the existing skill is the contract.

```bash
# Reference-guided generation (spritesheet Phase C, portrait-loop with reference)
python3 ~/.claude/scripts/nano-banana-generate.py with-reference \
    --prompt "<full prompt>" \
    --reference <canvas-or-ref-image> \
    --output <path> \
    --model pro \
    --aspect-ratio 1:1
```

```bash
# Portrait mode (no reference image needed)
python3 ~/.claude/scripts/nano-banana-generate.py generate \
    --prompt "<full prompt>" \
    --output <path> \
    --model pro \
    --aspect-ratio 4:5
```

`--model pro` (gemini-3-pro-image-preview) is the default for portrait/spritesheet because quality matters more than speed for canonical assets. Drafts can pass `--backend-flag --model=flash`.

## Capability matrix

| Capability | Codex CLI (v0.125+) | Nano Banana | Notes |
|------------|----------------------|-------------|-------|
| Single image from text | Yes (via `image_gen` tool) | Yes | Both work for portrait mode |
| Reference image input | Yes (`-i ref --`) | Yes (1 ref) | Codex accepts a list; Nano Banana single-ref |
| Multiple reference inputs | Yes | No | Codex passes 2+ via `-i` list with `--` terminator |
| Grid-template input for layout | Yes (with prompt instructions) | No | Codex consumes a magenta grid canvas as one of the `-i` references; Nano Banana lacks layout awareness |
| Aspect-ratio control | Encoded in prompt text | Full (10 ratios via flag) | Nano Banana has finer flag-level control |
| Seed reproducibility | Encoded in prompt text | Yes (via `--seed`) | Codex seed travels in the prompt body (no flag exposed) |
| Cost | User's Codex subscription | User's Gemini API key | Both billed under existing user accounts |

## Auth checks

| Backend | Auth check | Failure indicator | Fall-through? |
|---------|------------|-------------------|---------------|
| Codex CLI | `codex --version` returns 0 | Non-zero exit or timeout | Yes — try Nano Banana |
| Nano Banana | `GEMINI_API_KEY` or `GOOGLE_API_KEY` non-empty | Both empty | No — raise `BackendUnavailableError` |

Auth-check failures fall through to the next step rather than aborting the skill. Only step 3 (no backend at all) raises.

## Fail-loud message

When no backend is available, the user sees this exact message (or equivalent):

```
BackendUnavailableError: No image-generation backend available.

Fix path 1 (Codex CLI, recommended):
  Install Codex CLI and run `codex auth` to authenticate against your existing subscription.

Fix path 2 (Nano Banana fallback):
  Set GEMINI_API_KEY (or GOOGLE_API_KEY) in your environment to enable the Nano Banana fallback.
```

Both fix paths surface together. The user picks whichever is convenient; the skill does not prefer one over the other beyond the chain order.

## Backend-specific tweaks

`sprite_generate.py` adapts prompts when it knows the active backend:

| Tweak | Codex (v0.125+) | Nano Banana |
|-------|-----------------|-------------|
| Magenta-bg repetition | Repeat at start AND end of wrapped prompt | Single mention (compact prompts work better) |
| Negative-prompt block | Inline in main prompt | Inline (no separate negative-prompt API) |
| Aspect-ratio | Encoded in wrapped prompt text | `--aspect-ratio` flag |
| Reference-image weight | Pass via `-i ref --`; weight encoded in prompt | Strong (Nano Banana respects refs heavily) |
| Save instruction | "save to absolute path: <output>; verify with ls -la" | `--output <path>` flag |

These adaptations are applied automatically; the user does not specify them.

## Cost visibility

Both backends are billed under user-existing accounts:

- **Codex CLI**: monthly subscription; image generation counts against the subscription's token/image budget.
- **Nano Banana**: per-call billing on the user's Gemini API key. Free tier covers ~hundreds of generations per day; paid tier scales linearly.

`sprite_generate.py` logs which backend was used per call so the user can audit cost attribution after a batch run:

```
[backend] portrait gen for "bangkok_belle_nisa" → codex (call 1/8)
[backend] portrait gen for "general_gideon" → codex (call 2/8)
[backend] portrait gen for "test_subject_03" → nano-banana (call 3/8)  # codex auth refresh
...
```

The mid-batch backend switch is a feature: when Codex's auth token expires partway through a long batch, the chain auto-falls-through to Nano Banana so the batch completes rather than fail-loud-and-stop. The log records which calls hit which backend for cost attribution.

<!-- no-pair-required: section header; pair lives in subsection -->
## Failure Modes to Detect

### Signal: Adding a third paid backend as a silent fallback

**Detection:** "If Codex fails AND Gemini fails, try OpenAI directly with `OPENAI_API_KEY`" or "fall through to remove.bg for bg removal."

**Why wrong:** The user-owned-key clause (PHILOSOPHY.md, ADR-198) authorizes fallbacks gated on environment variables the user explicitly set — Codex auth and `GEMINI_API_KEY` qualify because the user holds the keys. A direct OpenAI API call billed to whoever set `OPENAI_API_KEY` is a different relationship: the toolkit is now picking which billing account gets charged. The user expects the documented chain (Codex → Nano Banana → fail loud); their card gets charged because step 3 quietly hit a paid endpoint they did not authorize. Trust violation, principle violation.

**Preferred Action**: Stop at the two authorized backends. Raise `BackendUnavailableError` at step 3 with both fix paths. If a third backend is genuinely needed, propose an ADR amendment that gates it on an explicit env var the user must set (the same pattern as `GEMINI_API_KEY` does for Nano Banana), so the fallback is explicit rather than silent.

### Signal: Caching auth state across runs without revalidation

**Detection:** Storing `BACKEND_DETECTED=codex` in a config file and trusting it on subsequent runs.

**Why wrong:** Codex auth tokens expire. `GEMINI_API_KEY` may be revoked. A cached "yes" can produce stale failures that look like the backend itself is broken.

**Do instead**: Run the detection logic at the start of every `sprite_generate.py` invocation. The check is fast (≤100ms for `codex --version`, instant for env-var check). Cheap to re-run; expensive to debug stale auth.

## Reference loading hint

Load when:
- Backend selection is failing (see fail-loud error above)
- Codex CLI version updates and the invocation contract may need amendment (current contract: v0.125+, ADR-198)
- Adding a new backend (rare; principle is two-step + fail-loud, requires ADR amendment)
- Debugging cost attribution across a batch run
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall