Plugin Claude Code
Frontier-grade engineering rigor for any model, in three layers: always-on discipline skills (claims, scope, native code, reporting, context), phased process for analysis and delivery (multi-agent deep-analysis audits, disciplined implementation, deep-work orchestration, adversarial verification, a risk-sized route…
Agent
Use this agent to execute ONE well-scoped implementation task end-to-end (a feature slice, bugfix, refactor step, or test batch) after the scope is already clear. Ideal for parallelizing independent slices of a larger build. Do NOT use it for ambiguous asks that still need owner decisions — clarify in the main…
Command
Independently re-check a conclusion, fix, or design by spawning an agent prompted to refute it — not affirm it.
Command
Multi-agent deep audit of the current project — adversarially verified findings + prioritized roadmap, published to docs/deep-analysis/.
Command
Run a large, multi-place, uncertain task to completion — plan, adversarial review, serial execute, synthesize & verify.
Command
Implement a feature, fix, or whole app with the full disciplined process — clarify, investigate, plan, build, verify, deliver.
Command
Show one feature's whole journey across the suite — idea → PRD → design → tasks → verified → regression-clean → shipped — by composing the existing per-plugin views (read-only; no new store).
Command
Prove a change didn't break existing work — run the suite + a bounded refute-first blast-radius probe vs docs/architecture/ contracts + honest coverage — and emit a structured regression verdict that taskmanager's done-gate enforces.
Command
Route a request to the right top-level pipeline by scope and risk — name the ordered sequence of existing entry points (analysis / trivial change / bug fix / feature-high-risk / health), advisory, then hand control back.
Hook
Runs when you submit a prompt, before the agent sees it, executing self_challenge_gate.sh, asset_inventory_gate.sh, ls_real_preflight.sh and session_retro.sh via bash (4 commands). From mwguerra/plugins.
Hook
Runs before the agent uses a tool for Bash and Bash tool calls, executing verify_before_commit.sh and verify_commit_gate.sh via bash (2 commands). From mwguerra/plugins.
Hook
Runs after a tool call finishes for Bash tool calls, executing restart_reminder.sh via bash. From mwguerra/plugins.
Hook
Runs when the agent finishes a response, executing verify_stop_gate.sh via bash. From mwguerra/plugins.
Skill Claude CodeCodex
Take a conclusion, code, fix, or design you just produced and spawn an independent agent to adversarially re-check it — assuming it likely missed something, with the job of finding holes rather than affirming. Trigger: you just reached an important conclusion/fix/design and want to confirm before delivering, or you…
Skill Claude CodeCodex
Use at the start of any multi-step task and during exploration — before reading files, searching, or re-checking completed work, especially when tempted to read whole files, re-verify known facts, or run independent lookups one at a time.
Skill Claude CodeCodex
Stay focused on the project with the task in hand; recall another project's knowledge ONLY when the task actually needs it. When a task requires changing a shared dependency you own (a local composer/npm package in another repo), make the change IN that owning repo — commit, push, retag — then update and re-verify the…
Skill Claude CodeCodex
Use when asked for a deep audit, deep analysis, production-readiness review, architecture assessment, or prioritized recommendations across a whole codebase or subsystem — orchestrates parallel reader agents with adversarial verification and publishes findings to docs/deep-analysis/.
Skill Claude CodeCodex
Run a large, multi-place, uncertain task to completion via "plan → adversarial review → serial execute → synthesize & verify." Trigger: cross-file refactor, data migration, large feature build, system audit, deep research — tasks that can't be done in one pass and touch many places. Manual invocation: /deep-work.
Skill Claude CodeCodex
Use before ending any turn that used tools or produced a deliverable — when tempted to ask "Want me to…?", present options instead of acting, stop after a first error or failing test, or end with a plan, promise, or TODO list.
Skill Claude CodeCodex
Use when asked to implement, build, add, fix, refactor, or change anything non-trivial in a codebase — especially vague asks ("do that", "make it work") that need clarification, planning, and verified delivery with tests and commits.
Skill Claude CodeCodex
Use when writing or editing code in an existing codebase — before adding comments, docstrings, try/catch blocks, validation, logging, or TODOs the surrounding file doesn't have, and before explaining your style choices in the reply.
Skill Claude CodeCodex
Use when writing any user-facing reply — answers, status updates, summaries, or final reports — especially after multi-step work, when tempted to show thoroughness, add headers or bullets to a short answer, open by classifying the question, or open with praise.
Skill Claude CodeCodex
Use before claiming anything works, is fixed, is done, or passes; before status updates on changes you haven't run; before agreeing with someone else's claim about your work; and before state-changing commands like restarts, deletes, or config edits.
Skill Claude CodeCodex
The discipline behind maestro:regression — prove a change didn't break existing work by running the suite, an adversarial bounded blast-radius probe against documented architecture contracts, and honest coverage, then emit a verdict taskmanager's done-gate enforces. Trigger: a change is about to be marked done /…