opencodekit 0.21.1 → 0.21.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (28) hide show
  1. package/dist/index.js +4 -4
  2. package/dist/template/.opencode/.template-manifest.json +721 -0
  3. package/dist/template/.opencode/.version +1 -1
  4. package/dist/template/.opencode/AGENTS.md +39 -29
  5. package/dist/template/.opencode/agent/vision.md +0 -1
  6. package/dist/template/.opencode/memory.db +0 -0
  7. package/dist/template/.opencode/memory.db-shm +0 -0
  8. package/dist/template/.opencode/memory.db-wal +0 -0
  9. package/dist/template/.opencode/opencode.json +1311 -1134
  10. package/dist/template/.opencode/plugin/README.md +10 -6
  11. package/dist/template/.opencode/plugin/rtk.ts +43 -0
  12. package/dist/template/.opencode/pnpm-lock.yaml +140 -706
  13. package/dist/template/.opencode/skill/agent-evals/SKILL.md +208 -0
  14. package/dist/template/.opencode/skill/anti-ai-slop/SKILL.md +76 -0
  15. package/dist/template/.opencode/skill/brand-asset-protocol/SKILL.md +222 -0
  16. package/dist/template/.opencode/skill/context-condensation/SKILL.md +149 -0
  17. package/dist/template/.opencode/skill/design-direction-advisor/SKILL.md +139 -0
  18. package/dist/template/.opencode/skill/hi-fi-prototype-html/SKILL.md +253 -0
  19. package/dist/template/.opencode/skill/html-deck-export/SKILL.md +189 -0
  20. package/dist/template/.opencode/skill/rtk-command-compression/SKILL.md +134 -0
  21. package/dist/template/.opencode/skill/test-driven-development/SKILL.md +15 -0
  22. package/package.json +1 -1
  23. package/dist/template/.opencode/package.json +0 -22
  24. package/dist/template/.opencode/plugin/package.json +0 -7
  25. package/dist/template/.opencode/plugin/stitch.ts +0 -307
  26. package/dist/template/.opencode/skill/stitch/SKILL.md +0 -164
  27. package/dist/template/.opencode/skill/stitch-design-taste/DESIGN.md +0 -121
  28. package/dist/template/.opencode/skill/stitch-design-taste/SKILL.md +0 -197
@@ -1 +1 @@
1
- 0.18.4
1
+ 0.21.3
@@ -21,7 +21,7 @@ Your loop: **perceive → create → verify → ship.**
21
21
  When instructions conflict:
22
22
 
23
23
  1. **Security** — never expose or invent credentials
24
- 2. **Anti-hallucination** — verify before asserting; if context is missing, prefer lookup over guessing; if you must proceed without full context, label assumptions explicitly and choose a reversible action
24
+ 2. **Anti-hallucination** — verify before asserting; if context is missing, prefer lookup over guessing; if you must proceed without full context, label assumptions explicitly and choose a reversible action. **Specific products / versions / launch dates / specs**: when the user names a real product (e.g. "DJI Pocket 4", "Gemini 3 Pro", a new SDK), always WebSearch its current state before answering. Forbidden phrases: "I think X hasn't launched", "X is currently version N" (without checking), "X probably doesn't exist", "as far as I know X's specs are…". Allowed: "Let me search for the latest state of X."
25
25
 
26
26
  ### Source Hierarchy
27
27
 
@@ -70,6 +70,8 @@ If a newer user instruction conflicts with an earlier one, follow the newer inst
70
70
  - Include effort signal when proposing work: **S** (<1h), **M** (1-3h), **L** (1-2d), **XL** (>2d)
71
71
  - Stop when "good enough" — note what signals would justify revisiting
72
72
 
73
+ **Trivial Task Escape Hatch.** When effort = **S** AND the change is reversible (typo fix, comment edit, single-line config tweak, isolated test addition), skip the heavy ritual: no Plan Quality Gate, no Worker Distrust Protocol, no Structured Termination Contract, no PRD. Just do it, run the relevant verification command, and report. Rigor scales with risk — don't pay overhead the change doesn't warrant.
74
+
73
75
  ### Anti-Redundancy
74
76
 
75
77
  - **Search before creating** — always check if a utility, helper, or component already exists before creating a new one
@@ -359,34 +361,42 @@ This ensures every prompt is execution-ready before work begins.
359
361
 
360
362
  When user intent is clear, load the appropriate skills:
361
363
 
362
- | Intent | Phase | Skills to Load |
363
- | ------------------------- | -------------- | ---------------------------------------------------------------------------------- |
364
- | "Build a feature" | Define → Build | `prd` → `writing-plans` → `incremental-implementation` + `test-driven-development` |
365
- | "Fix a bug" | Verify | `systematic-debugging` → `root-cause-tracing` |
366
- | "Review code" | Review | `receiving-code-review` or `requesting-code-review` |
367
- | "Simplify / refactor" | Review | `code-simplification` |
368
- | "Ship it" | Ship | `verification-before-completion` → `finishing-a-development-branch` |
369
- | "Plan this" | Plan | `brainstorming` → `prd` → `writing-plans` |
370
- | "Execute a plan" | Build | `executing-plans` + `subagent-driven-development` |
371
- | "Debug flaky tests" | Verify | `condition-based-waiting` + `systematic-debugging` |
372
- | "Debug in browser" | Verify | `chrome-devtools` or `playwright` |
373
- | "Write / fix tests" | Verify | `test-driven-development` + `testing-anti-patterns` |
374
- | "Build UI" | Build | `frontend-design` + `design-taste-frontend` |
375
- | "Build UI from mockup" | Build | `mockup-to-code` + `frontend-design` |
376
- | "Redesign existing UI" | Build | `redesign-existing-projects` + `design-taste-frontend` |
377
- | "Review UI / UX" | Review | `web-design-guidelines` + `visual-analysis` + `accessibility-audit` |
378
- | "Audit accessibility" | Verify | `accessibility-audit` |
379
- | "Build React / Next.js" | Build | `react-best-practices` + `frontend-design` |
380
- | "Research X" | Define | `deep-research` or `opensrc` |
381
- | "Design an API" | Build | `api-and-interface-design` + `documentation-and-adrs` |
382
- | "Set up CI/CD" | Ship | `ci-cd-and-automation` + `verification-gates` |
383
- | "Deploy app" | Ship | `vercel-deploy-claimable` |
384
- | "Deprecate / migrate" | Ship | `deprecation-and-migration` + `incremental-implementation` |
385
- | "Write docs / record ADR" | Define | `documentation-and-adrs` |
386
- | "Optimize performance" | Verify | `performance-optimization` |
387
- | "Harden security" | Verify | `security-and-hardening` + `defense-in-depth` |
388
- | "Verify before merge" | Ship | `reconcile` + `verification-gates` |
389
- | "Create a skill" | Build | `skill-creator` + `writing-skills` |
364
+ | Intent | Phase | Skills to Load |
365
+ | ----------------------------- | -------------- | ------------------------------------------------------------------------------------------------ |
366
+ | "Build a feature" | Define → Build | `prd` → `writing-plans` → `incremental-implementation` + `test-driven-development` |
367
+ | "Fix a bug" | Verify | `systematic-debugging` → `root-cause-tracing` |
368
+ | "Review code" | Review | `receiving-code-review` or `requesting-code-review` |
369
+ | "Simplify / refactor" | Review | `code-simplification` |
370
+ | "Ship it" | Ship | `verification-before-completion` → `finishing-a-development-branch` |
371
+ | "Plan this" | Plan | `brainstorming` → `prd` → `writing-plans` |
372
+ | "Execute a plan" | Build | `executing-plans` + `subagent-driven-development` |
373
+ | "Debug flaky tests" | Verify | `condition-based-waiting` + `systematic-debugging` |
374
+ | "Debug in browser" | Verify | `chrome-devtools` or `playwright` |
375
+ | "Write / fix tests" | Verify | `test-driven-development` + `testing-anti-patterns` |
376
+ | "Build UI" | Build | `frontend-design` + `design-taste-frontend` |
377
+ | "Build UI from mockup" | Build | `mockup-to-code` + `frontend-design` |
378
+ | "Redesign existing UI" | Build | `redesign-existing-projects` + `design-taste-frontend` |
379
+ | "Build branded design" | Build | `brand-asset-protocol` + `anti-ai-slop` + (target skill: frontend-design / hi-fi-prototype-html) |
380
+ | "Vague design brief" | Define | `design-direction-advisor` + `anti-ai-slop` |
381
+ | "Build hi-fi prototype" | Build | `hi-fi-prototype-html` + `anti-ai-slop` + `playwright` |
382
+ | "Build slide deck" | Build | `html-deck-export` + `anti-ai-slop` + (optional: `brand-asset-protocol`) |
383
+ | "Avoid AI design defaults" | Build / Review | `anti-ai-slop` |
384
+ | "Review UI / UX" | Review | `web-design-guidelines` + `visual-analysis` + `accessibility-audit` |
385
+ | "Audit accessibility" | Verify | `accessibility-audit` |
386
+ | "Build React / Next.js" | Build | `react-best-practices` + `frontend-design` |
387
+ | "Research X" | Define | `deep-research` or `opensrc` |
388
+ | "Design an API" | Build | `api-and-interface-design` + `documentation-and-adrs` |
389
+ | "Set up CI/CD" | Ship | `ci-cd-and-automation` + `verification-gates` |
390
+ | "Deploy app" | Ship | `vercel-deploy-claimable` |
391
+ | "Deprecate / migrate" | Ship | `deprecation-and-migration` + `incremental-implementation` |
392
+ | "Write docs / record ADR" | Define | `documentation-and-adrs` |
393
+ | "Optimize performance" | Verify | `performance-optimization` |
394
+ | "Optimize shell token usage" | Build / Verify | `rtk-command-compression` |
395
+ | "Harden security" | Verify | `security-and-hardening` + `defense-in-depth` |
396
+ | "Verify before merge" | Ship | `reconcile` + `verification-gates` |
397
+ | "Measure if a skill helps" | Verify | `agent-evals` |
398
+ | "Compress / hand off context" | Build | `context-condensation` + `context-management` |
399
+ | "Create a skill" | Build | `skill-creator` + `writing-skills` |
390
400
 
391
401
  ---
392
402
 
@@ -82,7 +82,6 @@ Use these when the user requests a specific visual direction or when your audit
82
82
  - `high-end-visual-design` — luxury/premium visual polish
83
83
  - `minimalist-ui` — editorial/clean, monochrome, sharp borders
84
84
  - `industrial-brutalist-ui` — experimental/CRT/Swiss mechanical aesthetic
85
- - `stitch-design-taste` — design rules aligned to Stitch export patterns
86
85
  - `full-output-enforcement` — when outputs are lazy/incomplete
87
86
 
88
87
  ## Design Taste Protocol (anti-slop)
Binary file