Add a least-privilege HOL Guard workflow, scanner policy, security reporting guidance, dependency monitoring, and immutable GitHub Action references. Align the Codex marketplace with its local plugin source and keep scanner verification reproducible for the awesome-ai-plugins submission.
- add native Claude Code plugin and marketplace manifests
- document Claude Code installation, invocation, updates, and removal
- reduce routing metadata and enforce a catalog budget
- validate Agent Skills and Claude manifests in CI
- remove wooyun-legacy from the package and provenance
- update package metadata and tests for the 54-skill catalog
Adds a design rubric for detecting generic AI output, with full
UPSTREAMS.json provenance. Updates skill count from 11 to 12 across
package metadata, README, and tests.
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.
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.
The "Critical: only HIGH-SIGNAL issues should be flagged" block appeared
twice, back to back, in code-review's SKILL.md and command. The second copy
was a strict subset of the first (it dropped the "Concrete edge cases"
bullet), so it was pure redundancy. The duplicate is removed; the complete
first copy stays.
The skill-lint suite gains a per-skill "no duplicated block" check (no
non-empty line >= 50 chars repeats within a SKILL.md or its command), which
catches this class of copy-paste error. SKILL.md and command stay in sync.
The skill described OpenCode's rules loading as a priority order between
AGENTS.md and CLAUDE.md. The actual behavior is first-match-wins per
directory: when both files coexist in the same directory, OpenCode loads
only AGENTS.md and silently ignores the CLAUDE.md.
This corrects the behavior description, replaces the tip that suggested
keeping an orphaned CLAUDE.md, and adds the shadowed-CLAUDE.md case to the
list of issues to flag. The skill's own description is also rewritten to be
more precise and trigger-specific; in the command it was previously
truncated mid-sentence. SKILL.md and command stay in sync.
opencode-power-pack bundles eleven Claude Code skills as an OpenCode plugin
under one config line, with each skill also exposed as a slash command.
Skills (by category):
Review
code-review multi-agent PR review with cross-check pass and
concrete reproduction scenarios
security-review OWASP-bucketed three-stage filtering with mandatory
PoC per finding
Feature dev
feature-dev seven-phase guided workflow
code-explorer deep codebase analysis sub-task
code-architect decisive architecture blueprint sub-task
code-reviewer two-pass adversarial review sub-task
Design
frontend-design distinctive, production-grade UI generation
Authoring
mcp-builder build high-quality MCP servers (Python or TypeScript)
skill-creator author new SKILL.md files
Project memory
agents-md-improver audit and update AGENTS.md / CLAUDE.md
agents-md-revise capture session learnings into the rules file
Architecture:
- .opencode/plugins/opencode-power-pack.js auto-registers skills/ via
config.skills.paths.push() (live config singleton modification, pattern
adapted from obra/superpowers).
- skills/<name>/SKILL.md hold the workflows the model executes.
- commands/<name>.md ship physical slash command files that inline the
full SKILL.md content, so the model receives the actual workflow as
its prompt rather than a meta-instruction. Symlinked into
~/.config/opencode/commands/ during install.
Almost all skill content is ported or translated from upstream Anthropic
projects (claude-code/plugins, skills, claude-code-security-review,
claude-plugins-official). The plugin loader pattern is adapted from
obra/superpowers. See README.md -> Acknowledgments for per-skill
attribution; each SKILL.md frontmatter also carries a license field
naming its specific upstream.