The planning documents for the behavioral evaluations workflow are
contributor-side working documents and should not land in main. Remove
them from the working tree and add gitignore rules so regenerated copies
do not reappear in future PRs.
- write reports and snapshots atomically, cleaning temp files on failure
- isolate CLI run tests from repository artifacts via env overrides
- cover version-detection failures, unsupported modes, manifest bounds,
redaction and grading edges, and malformed mutations with tests
- document path overrides and completed plan steps
Bumps package.json to 0.2.0 and updates the pinned-install examples in
README.md from #v0.1.0 to #v0.2.0. The historical "pre-v0.1.0 build" note
in Troubleshooting stays — it refers to an old cache state, not the
current version.
Covers Cursor, Windsurf, GitHub Copilot, Codex, Gemini, Aider, and
Continue, plus CLAUDE.local.md and AGENTS.local.md, so contributors
using any of those tools don't accidentally commit their private
context.
Adds a "files" whitelist to package.json so installing via
`opencode-power-pack@git+https://...` only ships what the runtime needs.
Tests, internal docs/validation, and CI config stay tracked in git but
no longer travel with the install.
feature-dev, code-architect, and mcp-builder gain a shared "Working
discipline" section (think before acting, simplicity first, surgical changes,
goal-driven). code-review and code-reviewer get a lighter touch — a "scope
creep" criterion added to their review checklists. security-review and
skill-creator already embody this discipline, so they are not modified, and
frontend-design is left alone because "simplicity first" would clash with the
skill's deliberate bold/maximalist direction.
The five command files are regenerated from their skills (in sync). A new
tests/working-discipline.test.mjs guards the additions so the rule cannot
silently regress.
The skill told the model to "edit whichever rules file the project already
uses." Under OpenCode's first-match-wins resolution, a CLAUDE.md co-located
with an AGENTS.md is never read, so learnings captured there would be silently
lost. The skill now describes first-match-wins and directs capture to
AGENTS.md when both exist (never the shadowed CLAUDE.md), reinforced in the
"where each addition belongs" step. A test guards it; command kept in sync.
Output of running the rewritten frontend-design skill in OpenCode on a NEBULA
sci-fi magazine brief: a dark editorial aesthetic with an acid-green accent, a
condensed display face (not Inter/Roboto), and three distinct pricing tiers.
Concrete evidence the skill produces distinctive, non-generic UI. Linked from
the PR's Validation section.
The skill already warned against converging on common choices, but the new
font and layout lists risk becoming the next default the way Space Grotesk
did. This adds an explicit "vary across generations" rule — treat the lists
as seeds to rotate, deliberately diverge when a brief resembles a prior one,
and never ship two different products as the same template. A matching
self-critique check rejects output that reads as a default pattern or a
previous generation. A test guards the rule; the command is regenerated from
the skill.
The skill was pure aesthetic prose with no self-review. This adds three
sections, reworded from cited sources and kept under 500 lines:
- Concrete anti-default moves: font-by-vibe picks, layout archetypes, type
contrast, semantic CSS-variable tokens, one orchestrated page-load.
- An objective self-critique rubric the model runs before returning (WCAG 2.2
AA contrast/semantics/alt/focus/reflow plus craft checks), framed honestly
since models tend to over-praise their own output.
- An optional, cross-platform validation note (html-validate static; pa11y or
axe for rendered DOM), including an opt-in vision-only Playwright screenshot
loop that text-only models skip.
Adds tests/frontend-design.test.mjs to guard the additions. The command is
regenerated from the skill and stays in sync.