Plugin Claude Code
Bundles 2 skills · 525 tokens together
Multi-agent adversarial review panel — 4-6 AI reviewers debate your code/plans, then a judge delivers a structured verdict with epistemic labels. Bundles plan-review-integrator for applying review findings back into implementation plans.
wan-huiyan/agent-traffic-control
Plugin Claude Code
Bundles 124 skills · 32,743 tokens together
Coordination toolkit for parallel Claude Code sessions sharing one repo — issue-pickup claim protocol (assignee + wip label), worktree & session-isolation pitfalls, parallel-PR conflict recovery, subagent-integrity edge cases, and squash/merge mechanics for parallel-PR workflows. Plus two opt-in hooks: leg-guard…
wan-huiyan/claude-ecosystem-hygiene
Plugin Claude Code
Bundles 1 skill · 199 tokens together
Counterfactual A/B + layered-ablation harness for Claude Code setup. Measures whether your /.claude/ stack (skills, lessons, axioms, memory) plus in-repo discipline (docs/runbooks, decisions, findings) actually helps on real tasks. Binary A/B (setup-ON vs setup-OFF) and layered ablation (strip one layer at a time, ran.
wan-huiyan/claude-ecosystem-hygiene
Plugin Claude Code
Bundles 1 skill · 308 tokens together
Wire up CI validation and automatic release-cutting for a Claude Code plugin or marketplace repo (one with a .claude-plugin/marketplace.json and plugins/). Adds two GitHub Actions — a structure validator on every PR/push, and a release-on-version-bump job that cuts a GitHub Release whenever VERSION changes — plus the.
wan-huiyan/claude-ecosystem-hygiene
Plugin Claude Code
Bundles 1 skill · 349 tokens together
Measure, trim, and report the token cost of a runaway Claude Code skills/agents catalog (injected every turn + into every subagent) — verified per-project skillOverrides + global disable-model-invocation levers, an interactive HTML recap, and the durable root-cause fix (curate episodic lessons out of the always-on…
wan-huiyan/claude-ecosystem-hygiene
Plugin Claude Code
Bundles 1 skill · 376 tokens together
Detect stale normative guidance in project docs/ after the user adds a new "don't X / avoid Y" rule to /.claude/lessons.md, /.claude/axioms.md, or a per-project feedback.md entry. Event-driven PostToolUse hook + weekly cron audit. Lists file:line candidate stale claims — never auto-edits. Conservative guardrails: e.
wan-huiyan/claude-ecosystem-hygiene
Plugin Claude Code
Bundles 1 skill · 342 tokens together
Full-coverage Claude Code ecosystem audit: skills usage from JSONL session logs, memory hygiene, handoff lifecycle, ADR integrity, worktree lifecycle scoring, and automation health. Produces an interactive HTML report with radar chart.
wan-huiyan/claude-ecosystem-hygiene
Plugin Claude Code
Bundles 1 skill · 162 tokens together
A check reported clean without examining the case it exists for — "green" meant "nothing ran". Use when about to trust a gate, test or CI step you have never watched fail; when a guard is green but the bug it guards shipped anyway; when a check passes on a shallow clone, a disabled object, a malformed input or an…
wan-huiyan/claude-ecosystem-hygiene
Plugin Claude Code
Bundles 1 skill · 166 tokens together
Audit and clean up Claude Code's persistent memory system — MEMORY.md, memory topic files, lessons, axioms, phase templates, ADRs, and the project docs/ taxonomy.
wan-huiyan/claude-ecosystem-hygiene
Plugin Claude Code
Bundles 1 skill · 204 tokens together
Pre-PR checklist and repo cleanup for data-science / analytics projects. Catches mistakes that cost hours later: data files committed to git (.csv/.db/.parquet), hardcoded /Users/ paths, tracked runtime artifacts, branch-ownership confusion, internal docs drifting from deliverables, and client data in public repos.…
wan-huiyan/claude-ecosystem-hygiene
Plugin Claude Code
Bundles 1 skill · 291 tokens together
Scan a portfolio of authored Claude Code skills and produce, per target repo, a precise list of which skills to ADD, which to UPDATE (with drift direction), and which to CROSS-LINK rather than copy. Uses per-repo function-level inclusion bars, portfolio deduplication (never recommend a skill already homed elsewhere)…
wan-huiyan/claude-ecosystem-hygiene
Plugin Claude Code
Bundles 1 skill · 177 tokens together
Quantitatively measure how effective a project's automated test suite is at catching real bugs, by replaying historical incidents at pre-fix commits and classifying CI failure history.
Plugin Claude Code
Bundles 1 skill · 256 tokens together
Add a cute, hand-authored SVG favicon to a web app. Three techniques (emoji, gradient blob, 16×16 pixel art) — ships with 56 pixel-art mascots and 22 emotion-variant gradient blobs.
Plugin Claude Code
Bundles 1 skill · 259 tokens together
Make a macOS terminal cute and then prove it renders: 463 built-in Ghostty themes, rounded Nerd Fonts, and a Starship prompt — plus a verify-glyphs script that catches the "?" boxes before the user sees them, and a per-terminal prompt split so Ghostty keeps its icons while Apple Terminal, VS Code and ssh get a prompt…
Plugin Claude Code
Bundles 1 skill · 216 tokens together
Author a cute, high-signal GitHub README in a polished house style: a pixel/arcade hero, a badge row, a bold one-line value prop, a captioned demo image, an emoji feature table, a copy-paste install block, a contributors shoutout, and an honest limitations section. Ships a fill-in template + baked-in hero recipes…
Plugin Claude Code
Bundles 1 skill · 185 tokens together
Add cute, zero-dependency page effects to a web app: a fairy-wand custom cursor, sparkle trail on mouse move + click, an animated floating scroll-depth/progress indicator, tab-title peekaboo, click confetti / heart burst, ambient floaters (petals/bubbles/snow), and cute-chrome touches (::selection, wobble hover…
Plugin Claude Code
Bundles 1 skill · 247 tokens together
End-of-session handoff with bucket-aware dispatch across the canonical 7-bucket docs/ taxonomy (aligned with memory-hygiene v3.3), doc-freshness reverse-lint + skill-freshness audit, and future-to-do emission as GitHub issues. Captures knowledge, routes artifacts to…
Plugin Claude Code
Bundles 1 skill · 163 tokens together
Mid-run agent-to-agent handoff for long autonomous workflows. Lean parent orchestrator + file-first subagents + successor dispatch when context pressure rises.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: