askwigconsulting

askwigconsulting/cohort

Command

Get a second opinion from ChatGPT (via the OpenAI Codex CLI, read-only) on a hard problem — advisory, cross-examined, never executed blindly.

askwigconsulting/cohort

Command

Get a second opinion from Grok (via xAI's API, direct) on a hard problem — advisory, cross-examined, never executed blindly.

askwigconsulting/cohort

Command

Cross-vendor build — a coordinator routes work to the cheapest capable model from any vendor; Claude subagents write, external engines propose gated patches.

askwigconsulting/cohort

Command

Rate an office agent or command from inside the IDE (fuels the improvement loop).

askwigconsulting/cohort

Command

Drive a GitHub issue to a draft PR — build, then an independent judge verifies each criterion (max 3 rounds).

askwigconsulting/cohort

Command

Interview the user and tailor the global office — wiring, context, and custom agents.

askwigconsulting/cohort

Command

Break work into small verifiable tasks with acceptance criteria and dependency ordering.

askwigconsulting/cohort

Command

Interview the team about this repo — fill project context and scaffold tailored specialists.

askwigconsulting/cohort

Command

Metric-gated autonomous optimization loop — propose, evaluate, keep the gain or revert, in a throwaway worktree; you review the staircase and merge.

askwigconsulting/cohort

Command

Multi-vendor adversarial review — fan disjoint areas to Claude tiers, ChatGPT, and Grok, cross-examine over two rounds, synthesize with convergence.

askwigconsulting/cohort

Command

Run the pre-launch checklist via parallel fan-out to specialist personas, then synthesize a go/no-go decision.

askwigconsulting/cohort

Command

Capture a session snapshot for this repo's Cohort context, filled from this conversation.

askwigconsulting/cohort

Command

Start spec-driven development — write a structured specification before writing code.

askwigconsulting/cohort

Command

Run TDD workflow — write failing tests, implement, verify. For bugs, use the Prove-It pattern.

askwigconsulting/cohort

Command

Update Cohort to the latest upstream version and recompile your IDEs.

askwigconsulting/cohort

Agent

An agent that targets only codex, to prove the claude renderer skips it.

askwigconsulting/cohort

Skill Claude CodeCodex

Assemble a dated weekly report from session logs and git history.

askwigconsulting/cohort

Skill Claude CodeCodex

How to run a multi-vendor adversarial review — disjoint areas, model/vendor routing, two-round refutation, convergence synthesis (the /scout method).

askwigconsulting/cohort

Skill Claude CodeCodex

Four sharp coding rules (Karpathy) — think before coding, simplicity first, surgical changes, goal-driven — as measurable tests, complementing fable-mode's process gates.

askwigconsulting/cohort

Skill Claude CodeCodex

How to work with the Cohort agentic office — routing, the daily loop, health checks.