andrem-sec/psc-comet

library-pipeline

Convert PDF/EPUB library to Markdown and generate Obsidian MOC notes

strategic-compact

Hook-based compaction suggestions at logical task boundaries

token-budget

Context window management — track spend, decide when to compact, preserve state

heartbeat

Session-start orientation — loads context, surfaces learnings, confirms registry

code-review

Quality and semantic review — catches what automated tools miss

consensus-plan

Planner → Architect → Critic deliberation loop — produces a formally validated ADR

doc-review

Dual-dimension document quality gate — presentation rubric + hallucination grounding check

model-router

Model selection guidance — match task complexity to model capability

reasoning-gates

Scan task for high-cost branch points, confirm which get deep reasoning, execute with gates active

resume

Resume an interrupted mid-task session — reconstructs state from context files and picks up at the right step

feature-pipeline

Full feature workflow — deep-interview → prd → consensus-plan → tdd → code-review → security-gate

plan-first

Plan-mode enforcement — required before edits affecting 3+ files, cross-domain work, or security-sensitive changes

wrap-up

Session-end protocol — collect learnings, update context, commit session state

agentic-engineering

Framework for decomposing agent-driven tasks into independently verifiable units

reflect

Extract instinct candidates from the current session and add confirmed ones to the instinct store

eval-harness

Eval-driven development with pass@k metrics and three grader types

learner

Capture codebase-specific knowledge as a reusable skill — passes 3-point quality gate before writing

lesson-gen

Mid-session quick capture — save an insight before the context moves on

project-scan

Auto-populate context/project.md by reading the current codebase

remember

In-session memory tagging — mark content for recall later in the same session

roe

Rules of Engagement authorization gate — required before any security operation, autonomous scanning, or action with real-world effects outside the local codebase

security-gate

Pre-deploy security assessment — validates against OWASP Top 10 and project standards

jwt-algorithm-confusion-prevention

Prevent algorithm confusion attacks when validating JWTs — RS256 tokens accepted as HS256

ui-ux-pro-max

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind,…

agent-harness-construction

Framework for designing quality agents with proper action space and contracts

ai-regression-testing

Test specifically for AI-introduced regressions that repeat without tests

animation-safe

Audit animations and transitions for motion accessibility, performance safety, and design intent. Enforces prefers-reduced-motion compliance and blocks layout-triggering transitions.

batch

Parallel agent swarm — decomposes work into independent units, spawns isolated workers, tracks PRs via fan-in

benchmark

Performance measurement with Core Web Vitals thresholds — baseline capture, regression detection, optional PageSpeed Insights

brand-context

Load and validate brand assets before any design work — logo, colors, typography, voice. Gates UI and marketing work behind confirmed brand context.

canary

Post-deploy production monitoring — watches live app for errors, regressions, and failures after deployment

checkpoint

Named decision point for long-running tasks — PIVOT, REFINE, or PROCEED

codebase-onboarding

4-phase systematic codebase onboarding with reconnaissance and artifact generation

component-spec

Define component API, states, variants, and ARIA requirements before writing a line of implementation code. Gates component work behind a confirmed spec.

context-budget

Token audit across agents, skills, and MCP with cost optimization guidance

continuous-learning-v2

Cross-session instinct learning with confidence-based promotion and global scope

cso

Chief Security Officer mode — multi-phase security audit covering OWASP, STRIDE, secrets, CI/CD, and LLM attack surfaces

debug-session

Structured debugging protocol — hypothesis-driven investigation with evidence tracking

deep-interview

Socratic problem exploration — identifies critical unknowns and gates on ≤20% ambiguity before proceeding

deep-research

6-step multi-source research workflow with inline citations and synthesis