bstack

Plugin bstack from marketplace agent-kit in lyddonb/agent-kit. Commands read from the repo's manifest — 2 days ago.

Skills (23)

• architect

  Design before code. Ground in the affected systems, sketch types and signatures in at least two structurally different shapes (via arena), pick one, implement against it, and scrap it when friction shows the shape is wrong. Use for /architect, "design this", or work where jumping to code would lock

• arena

  Run N parallel candidates at the same task (ideally on different models), have a judge on another model score them against a rubric, pick a base, and graft the best parts of the others into it. Use for /arena, "arena this", "throw it in the arena", or when one attempt at a non-trivial artifact (a de

• beau-help

  List what agent-kit and bstack can do (skills, playbooks, subagents) and how to call each one, or show what changed since you last looked. Use for /beau-help, "what can you do", "which skill should I use for X", "what's new", or "what changed in bstack".

• beau-mode

  Beau's way of doing engineering work with an agent. It picks a playbook, applies named principles, verifies on the real artifact, keeps a decision trail, and writes plain replies. Use for /beau-mode, "beau mode", or any non-trivial engineering task (a bug, a feature, a refactor, a perf problem, an i

• correct

  Find the mistakes agents keep repeating in this repo and make each one impossible. Tries architecture first, then types, then a lint or CI check whose error names the fix, then a test, and docs last, and proves each new check fails on a real past mistake. Use for /correct, "agents keep doing X", or

• create-formal-verification-skill

  Generate a project-local verify-AREA skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits (model checker, prover, SMT-backed verifier). Use for /create-formal-verification-skill, "model-check this race", "p

• create-verification-skill

  Generate a project-local verify-APP skill (for example verify-curator) that launches the real app, drives it like a user through a control CLI, captures evidence, and keeps a feature map. Any stack or surface. Use for /create-verification-skill, "make a control skill for this repo", or when a projec

• figure-it-out

  Design a rigorous, auditable playbook for work no standard playbook fits (a large migration, an ambitious multi-part change, or anything the human will review after stepping away), then run it as a hypothesis loop with a decision trail. Use for "figure it out", large or cross-cutting changes, or ove

• how

  Explain how a subsystem, feature or code path works, at the level a senior engineer needs before changing it, covering runtime flow, key concepts, where things live and gotchas. Use for "how does X work", walkthroughs before a change, onboarding to unfamiliar code, and "where should this live" or "w

• interrogate

  Adversarial multi-model review of a diff, branch, PR or design. Several adversaries try to break it, and a finding survives only when a run proves it. Use for "interrogate", "adversarial review", "tear this apart", "stress test this change", "find blind spots", or before shipping a contested or risk

• maintain-formal-verification-skill

  Bring a project's formal verification back in line with the code after the code changes. Finds the commits that touched verified code, updates the model, harness or properties to describe the code as it is now, reruns, and says whether each failure is drift in the verification or a bug in the code.

• maintain-verification-skill

  Periodic pass that keeps a project's verification skill and feature map honest. Read-only subagents check each feature against source, one live session drives every feature, and at most one PR ships proven corrections. Use for /maintain-verification-skill, "audit the verify skill", "is the feature m

• recall

  Rebuild the user's recent context on a topic from their own agent transcripts, the PRs, tickets and reports around it, and live git state, then return a short brief and the next move. Use for "recall my work on X", "catch me up on X", "where did I leave off", before starting or resuming work.

• reflect

  Mine the current session for durable lessons and turn each one into a concrete, approved edit to a skill, playbook or principle, or a backlog item. Three independent reviewers read the transcript, a synthesizer sorts their findings, and nothing changes without the user's approval. Use when the user

• scaffold-product

  Set up a repo for product work with agents, either a new product or an existing repo that predates this workflow. Writes the vision, decision log, phase specs, roadmap and agent instructions, then creates its verification skill, and checks the result with check-product.py. Use for "start a new produ

• show-me-your-work

  Keep a reviewable decision trail for long, unattended or multi-phase work (one TSV row per decision with what, why, evidence and result), then audit it against the transcript and have a different model flag what deserves attention. Use for /show-me-your-work, "keep a decision log", autonomous or ove

• state-machines

  Find the implicit state machines in a codebase (lifecycles spread across booleans, status strings, nullable fields, effects and handlers), show which states conflict with exact lines, then make them explicit as a checked spec and a pure transition function with IO at the edge. Use for "find all the

• swarm

  Fan out N parallel workers (local subagents, or cloud agents where your tool has them), wait for all of them, and return one consolidated report. Use for /swarm, "swarm this", parallel coverage of many slices, races of N attempts at one brief, live-verification lanes, fuzzing, or collecting enough p

• teach

  Explain a body of work plainly so a person actually understands it, by running the how and why skills and weaving what they find into one clear, layered explanation with diagrams that build up step by step. Use for "teach me this", "help me really understand X", "explain this change or subsystem to

• technical-writing

  Layered technical-writing standard (Diátaxis structure, Google developer style sentences, Simplified Technical English instruction rules, Global English syntax). Use for /technical-writing, README-driven planning, or when writing or reviewing docs, READMEs, RFCs, design docs, plans, PR descriptions

• unslop

  Cut AI writing tells from prose, such as filler, inflated vocabulary, em dashes, rule-of-three padding, chatbot phrases, vague metaphors, over-compression. Use when writing or reviewing any prose (replies, docs, READMEs, PR descriptions, commit messages, skill files), or when asked to unslop, tighte

• verify-work

  Prove a change works by checking the real artifact (run the feature, read the actual value, drive the real surface) and return VERIFIED, NOT VERIFIED or INCONCLUSIVE with evidence. Use before saying any task is done, when asked "does it work", "prove it", "verify", or when a claim rests on "it compi

• why

  Find out why code is the way it is (design rationale, past decisions, regressions, where a threshold came from) by searching git, PRs and every connected ticket, doc, chat and observability tool in parallel, and return a cited, confidence-tiered answer. Use for "why does X work this way" or "why did

Subagents (1)

• beau-agent

  Subagent for code-writing and investigation steps inside beau-mode playbooks. Spawn a fresh one per task. It loads the beau-mode skill and its principles index before any work, so it follows the same playbooks, principles and verification bar as the parent.

Hooks (1)

• SessionStart

  python3 "${CLAUDE_PLUGIN_ROOT}/skills/beau-help/scripts/whats_new.py" --hook

Similar plugins