andrem-sec/psc-comet

library-pipeline

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

Idioma del texto original: inglés

strategic-compact

Hook-based compaction suggestions at logical task boundaries

Idioma del texto original: inglés

token-budget

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

Idioma del texto original: inglés

heartbeat

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

Idioma del texto original: inglés

code-review

Quality and semantic review — catches what automated tools miss

Idioma del texto original: inglés

consensus-plan

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

Idioma del texto original: inglés

doc-review

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

Idioma del texto original: inglés

model-router

Model selection guidance — match task complexity to model capability

Idioma del texto original: inglés

reasoning-gates

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

Idioma del texto original: inglés

resume

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

Idioma del texto original: inglés

feature-pipeline

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

Idioma del texto original: inglés

plan-first

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

Idioma del texto original: inglés

wrap-up

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

Idioma del texto original: inglés

agentic-engineering

Framework for decomposing agent-driven tasks into independently verifiable units

Idioma del texto original: inglés

reflect

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

Idioma del texto original: inglés

eval-harness

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

Idioma del texto original: inglés

learner

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

Idioma del texto original: inglés

lesson-gen

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

Idioma del texto original: inglés

project-scan

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

Idioma del texto original: inglés

remember

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

Idioma del texto original: inglés

roe

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

Idioma del texto original: inglés

security-gate

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

Idioma del texto original: inglés

jwt-algorithm-confusion-prevention

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

Idioma del texto original: inglés

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,…

Idioma del texto original: inglés

agent-harness-construction

Framework for designing quality agents with proper action space and contracts

Idioma del texto original: inglés

ai-regression-testing

Test specifically for AI-introduced regressions that repeat without tests

Idioma del texto original: inglés

animation-safe

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

Idioma del texto original: inglés

batch

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

Idioma del texto original: inglés

benchmark

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

Idioma del texto original: inglés

brand-context

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

Idioma del texto original: inglés

canary

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

Idioma del texto original: inglés

checkpoint

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

Idioma del texto original: inglés

codebase-onboarding

4-phase systematic codebase onboarding with reconnaissance and artifact generation

Idioma del texto original: inglés

component-spec

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

Idioma del texto original: inglés

context-budget

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

Idioma del texto original: inglés

continuous-learning-v2

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

Idioma del texto original: inglés

cso

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

Idioma del texto original: inglés

debug-session

Structured debugging protocol — hypothesis-driven investigation with evidence tracking

Idioma del texto original: inglés

deep-interview

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

Idioma del texto original: inglés

deep-research

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

Idioma del texto original: inglés