20 production-grade skills for AI coding agents — setup, scope, discipline, code review, security, session management, governance, ops, and quality audits (eval-leakage, doc-drift). Works with Claude Code, Codex, and Cursor.
Plugin Claude Code
Bundles 1 skill · 0 tokens together
Carves safety-adjacent requests into a safe scope, executed by a genuinely isolated fresh-context subagent, with an adversarial verify pass and a descope ledger.
Plugin Claude Code
Bundles 1 skill · 3 tokens together
12Q quantified code review — 4-axis scoring (Security/Stability/Robustness/Operability), severity anchors, deployment verdict, factuality gate. Works as standalone prompt in any LLM.
Plugin Claude Code
Bundles 1 skill · 179 tokens together
13-section AI collaboration audit — analyzes actual work patterns (not surveys) to generate behavioral profile, blind spots, and growth direction.
Plugin Claude Code
Bundles 1 skill · 223 tokens together
Audits the memory and documents Claude Code loads into context (CLAUDE.md, MEMORY.md, skills, agents, commands, plugins) for outdated claims, contradictions, and risky/ambiguous wording. Produces a prioritized report at .drift-reports/.
Plugin Claude Code
Bundles 1 skill · 136 tokens together
Audits whether an eval/metric/experiment/holdout secures independent external ground truth or is circular via an 8-pattern taxonomy. Read-only.
Plugin Claude Code
Bundles 1 skill · 30 tokens together
Declare the editable zone — everything outside is frozen. Prevents scope creep during implementation by locking untouched files.
Plugin Claude Code
Bundles 1 skill · 161 tokens together
Exhaustive audit of an entire area (codebase/docs/skills/memory/config) — deterministic sweep + content review, anti-false-positive kill-test, persistent coverage map.
Plugin Claude Code
Bundles 1 skill · 49 tokens together
Agent discipline engine — locks the goal, enforces PLAN-DO-VERIFY-FINALIZE-OUTPUT loop, detects 13 success masquerading patterns.
Plugin Claude Code
Bundles 1 skill · 66 tokens together
5-item screening gate for adopting external patterns (skills/agents/rules/plugins/MCP), with a provenance/injection check for imported executable content.
Plugin Claude Code
Bundles 1 skill · 57 tokens together
Reads handoff/git/lessons/STATE and proposes top-3 next actions by impact. Proposes only, never executes.
Plugin Claude Code
Bundles 1 skill · 144 tokens together
Mandatory pre-push pipeline — secrets scan (12 patterns), build/test gate, lint, parallel AI code review. Blocks push on Critical/High findings.
Plugin Claude Code
Bundles 1 skill · 81 tokens together
Scan existing project across 4 dimensions: Infrastructure, Security, Quality, Harness. Returns scored gaps ordered by severity.
Plugin Claude Code
Bundles 1 skill · 82 tokens together
Interview-based project scaffolding for Claude Code — generates CLAUDE.md, ROADMAP, .gitignore, and .env.example from decisions, not templates.
Plugin Claude Code
Bundles 1 skill · 109 tokens together
Generates a deterministic cross-project status map from registered projects' session handoffs.
Plugin Claude Code
Bundles 1 skill · 115 tokens together
Define what is IN, what is OUT, and exit criteria before implementation. Quick mode (3 questions) or Full mode (layered spec with ADR).
Plugin Claude Code
Bundles 1 skill · 44 tokens together
Session closer — saves context before compact. Handoff file, memory updates, lesson extraction, reflexion (what went wrong, what to improve).
Plugin Claude Code
Bundles 1 skill · 52 tokens together
Session opener — loads handoff from last session, reviews lessons learned, runs health check, outputs ready signal with priority action.
Plugin Claude Code
Bundles 1 skill · 77 tokens together
Claude Code infrastructure and agent team setup — rules, hooks, memory system, routing, and agent installation in one guided flow.
Plugin Claude Code
Bundles 1 skill · 18 tokens together
Skill ops hub: snapshot/rollback, usage health, and invocation tracking for Claude Code skills and agents.
Plugin Claude Code
Bundles 1 skill · 51 tokens together
One-shot perspective reset — 1 reframing question + 3 quick checks in under 10 lines.
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: