gabbe

Plugin gabbe from marketplace gabbe in andreibesleaga/GABBE. Commands read from the repo's manifest — yesterday.

Skills (44)

• agent-analytics

  Tracks key performance indicators (KPIs) for AI Agents: Token Usage, Task Duration, Loop Cycles, and Success Rate. Use when: analytics, metrics, tokens used, cost tracking, performance report, agent stats.

• agentic-linter

  Enforce architecture layer boundaries defined in AGENTS.md — detect and fix import violations. Use when: architecture lint, boundary, import violation, layer check, ADD, circular dependency, dependency check.

• api-design

  Design REST/GraphQL/OpenAPI contracts before implementation — API-first approach. Use when: API, endpoint, REST, GraphQL, OpenAPI, API contract, API design, HTTP endpoint, grpc, soap.

• arch-design

  Design system architecture from approved requirements — quality attributes, style selection, arc42/4+1 views, ADRs. Use when: design architecture, new architecture, architect the system, system design, choose architecture, architectural design, create architecture, system structure.

• arch-review

  Review existing architecture (ATAM-lite) against quality-attribute scenarios; find risks, tradeoffs, anti-patterns; report. Use when: review architecture, audit architecture, architecture analysis, architecture assessment, arch review, evaluate architecture, is the architecture good, architecture pr

• audit-trail

  Maintain append-only structured audit log of all agent and human decisions and outcomes. Use when: log this, record decision, why did we, audit, what happened, history, trace, record this.

• brain-mode

  Meta-cognitive orchestrator — adds Active Inference, cost-routing, and episodic memory to the SDLC loop (System-2 planning). Use when: brain activate, supermode, solve everything, brain mode, meta orchestrate.

• clarify

  Generate high-quality clarifying questions for any task/step, escalating when self-estimated uncertainty is high. Use when: clarify, clarifying questions, what should I ask, ambiguous, unclear, questions for you, are you sure, confirm requirements, what do you mean.

• clean-coder

  Enforces Clean Code standards, identifies code smells, and ensures SOLID principles. Use when: clean code, code smell, SOLID, refactor, quality check.

• code-review

  Systematic code review covering security, performance, architecture, and style. Use when: review, PR, audit, code quality, pull request, check this code.

• cost-benefit-router

  Intelligent routing of tasks between Local (OS) and Remote (Cloud) resources based on complexity, privacy, and cost constraints. Use when: route task, optimize cost, choose model, local or remote.

• debug

  Systematic root-cause debugging — reproduce, isolate, hypothesize, fix with TDD. Use when: bug, error, fix, broken, crash, exception, not working, unexpected behavior, regression.

• decompose

  Decompose specs/plans into atomic, testable tasks — enforces the 15-Minute Rule and populates project/TASKS.md. Use when: decompose, break down tasks, create task list, task decomposition, 15 minute rule.

• documentation

  Generate docstrings, JSDoc, API docs, and README updates that reflect current code. Use when: docs, docstring, JSDoc, README, API docs, document this, add documentation.

• emerging-tech

  Architecture assistance for 2026-2030 technologies (6G, Matter IoT, Vector DBs). Use when: 6g, iot, matter, vector, embedding, semantic search, rag, edge native, post-quantum.

• empirical-methods

  Apply empirical and measurement methods to engineering decisions with sound experiment design, honest statistical interpretation, and root-cause analysis. Use when: design a controlled experiment, interpret benchmark statistics, analyze a b test results, choose measurement scale and metric, check ef

• final-review

  Expert end-of-work review — catch errors/gaps/risks and propose optimizations before declaring done. Use when: final review, expert review, review everything, anything missing, make it better, optimize, simplify, sanity check, ship check, is it good.

• git-workflow

  Conventional commits, PR creation, and quality gate verification. Use when: commit, PR, branch, push, conventional commit, create pull request, git.

• integrity-check

  End-to-end 8-dimension verification — requirements through delivery, all aligned and correct. Use when: integrity, verify all, are we done, is it complete, end-to-end check, check everything, full verification.

• knowledge-connect

  Manage knowledge integration via MCP, Vector DBs, and A2A connectors. Use when: Connect to knowledge base, Ingest documentation, Query vector database, Setup RAG pipeline, Index project files.

• knowledge-gap

  Detect unknown territory before acting — a research gate forcing authoritative verification of unknown APIs/libraries. Use when: not sure, unfamiliar, haven't used, unknown API, new technology, not familiar with, unsure how, I don't know.

• loki-mode

  Master multi-agent swarm orchestration — coordinates personas across the 14-phase lifecycle (10-phase core build loop S01–S10, plus Day-0 S00 and Day-2 S11–S13) with checkpoints, memory, and HITL gates. Use when: loki, swarm, orchestrate, big project, autonomous build, multi-agent, spawn, coordinate

• meta-prompting

  Agents optimizing prompts for other agents (Chain of Thought, Tree of Thoughts). Use when: meta prompting.

• persona-selector

  Rank/select the best Loki persona(s) per task; persona delegation, consensus voting, bounded self-refinement — cost-gated. Use when: persona selector, best persona, which agent, pick persona, delegate to persona, route task, assign persona, who should do this, persona voting.

• preflight

  Mandated first action — auto-check, load index summaries + memory + cost, recommend the optimal set, then clarify. Use when: preflight, session start, before anything, start, begin, kickoff, what should I use, load context, orient, first step.

• refactor

  Safe refactoring with test guard — improve code quality without changing behavior. Use when: refactor, cleanup, restructure, simplify, extract function, improve code quality.

• req-elicitation

  Structured requirements elicitation — derive complete, verifiable requirements from stakeholder goals (IEEE 29148, IREB, EARS). Use when: elicit requirements, gather requirements, what are the requirements, new product requirements, user needs, stakeholder goals, write PRD, requirements from scratch

• research

  Find authoritative answers from official docs, RFCs, standards, and academic sources — never from blogs or opinions. Use when: research, find, how to, unknown, best practice, which library, official docs, RFC, spec, standard, look this up.

• retrospective

  Run a blameless retrospective — gather a timeline, generate insights, decide a few owned dated actions, and feed lessons into CONTINUITY.md memory. Use when: run a retrospective for the release milestone, do a blameless retro on the sprint, what went well and what didnt, capture lessons learned into

• safety-scan

  Active security enforcement — scan for vulnerabilities (SAST), secrets (Gitleaks), insecure deps (SCA) before commit/deploy. Use when: scan security, check vulnerabilities, audit code, gitleaks, semgrep, finding secrets.

• sdlc-checkpoint

  Save SDLC milestone snapshot, verify phase gates, advance tracking, and tag git commit. Use when: checkpoint, milestone, end of phase, requirements approved, design done, ready to code, sprint done, phase complete.

• secure-coding

  Implementing OWASP Proactive Controls (Input Validation, Output Encoding, AuthZ/AuthN). Use when: secure coding.

• security-audit

  OWASP Top 10 security audit, SAST/DAST/SCA scanning, secrets detection, and dependency vulnerability check. Use when: security, vulnerability, OWASP, secrets, CVE, security audit, security scan, penetration.

• self-heal

  Autonomous diagnose-research-fix-verify loop — up to 5 attempts before human escalation. Use when: test failing, error, self-heal, stuck, broken, can't fix, autonomous fix, retry, fix this.

• self-optimize

  Tune skill/guide/persona/model selection to the project for quality+cost; gabbe.config.json + autonomy levels + alignment. Use when: self optimize, optimize for project, tune selection, best for this project, project config, autonomy level, optimize quality cost, adapt to project.

• session-resume

  Cold-start resume — load all memory and project state to continue any interrupted project. Use when: resume, continue, new session, where were we, restart project, pick up, interrupted, cold start.

• skills-registry

  Discover, import, and publish skills to/from universal SKILL.md registries (Agent Garden, skills.sh, …) — validated + gated. Use when: skills registry, import skill, publish skill, agent garden, skills marketplace, draw skill, share skills, external skill, skills.sh.

• spec-writer

  Generate Product Requirements Document with EARS syntax and structured ambiguity clarification. Use when: spec, PRD, feature, requirements, product requirements, write spec, new feature.

• state-portability

  Dehydrate/hydrate full working state into a portable, agent-agnostic bundle — switch coding agent or LLM and continue. Use when: hydrate, dehydrate, export state, import state, switch agent, switch llm, portable state, handoff, migrate session, take my work elsewhere, continue on another agent.

• state-preserve

  Continuously persist working state + a resume pointer so a token/time/crash cutoff never loses progress — resume losslessly. Use when: save state, preserve state, checkpoint, dont lose progress, running out of tokens, time limit, flush state, persist, before stopping, resume pointer.

• system-lifecycle

  Orchestrate the full SDLC from Requirement to Code to Test (Traceability). Use when: lifecycle, traceability, requirement, golden thread, definition of done, verify requirements.

• tdd-cycle

  Red-Green-Refactor TDD loop with mandatory false-positive check. Use when: test, TDD, red-green, failing test, write test first, test-driven.

• threat-model

  STRIDE threat modeling before implementing security-sensitive features. Use when: threat, STRIDE, attack surface, security design, new API, new feature security, threat model.

• update-scan

  Discover new skills/tools/MCPs/models; recommend or auto-adopt the best per scenario within cost + permission bounds. Use when: update scan, check for updates, new tools, better model, newer skill, whats new, self-evolve, upgrade, scan registry, better mcp.

Similar plugins