Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/askwigconsulting/cohort/consult-grokgit clone --depth 1 https://github.com/askwigconsulting/cohortWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/askwigconsulting/cohort/consult-grok)<a href="https://agentmods.dev/commands/askwigconsulting/cohort/consult-grok"><img src="https://agentmods.dev/badge/commands/askwigconsulting/cohort/consult-grok.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00035 | $0.00987 |
| Opus 5 | $0.00017 | $0.00494 |
| Sonnet 5 | $0.00007 | $0.00197 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
consult-grok scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bring a second model into the room. /consult-grok asks Grok (via xAI's API,
direct) for an independent opinion on a hard problem — a design choice, a tricky bug,
a plan worth cross-examining. Grok joins the office on the office's terms: advisory
only. It recommends; Claude weighs; the human decides.
1. Prefers the local sandboxed CLI, falls back to API-direct
When grok-cli and bubblewrap are installed, the consult runs through the local grok CLI inside a throwaway, bubblewrap-sandboxed worktree — so grok reads this repo's committed files to answer, not only the packaged prompt (real local context). Any writes it makes are confined to that worktree and discarded; it stays read-only and advisory. When grok-cli/bwrap isn't present, grok is reached API-direct instead — text only, no local access — with a printed note. Either way, package the context and the question, write the prompt to a temporary file, and call:
cohort engine consult grok --prompt-file <f>
Never pass the prompt as an inline shell argument — write it to a file first, then pass the file path. The consult is advisory in both modes — it recommends, Claude weighs, the human decides — and nothing is written to this repo.
Model choice defaults to the engine's flagship tier. Ask for a tier by name
(--tier flagship | cheap | reasoning), not for a vendor alias: xAI's aliases silently
resolve to a different model than their name suggests — grok-4-latest serves grok-4.3,
not the flagship — so the registry pins concrete, probed ids and the tier name is the only
thing that reliably gets you the model you asked for. cohort engine consult grok --tier nonsense lists the tiers this engine actually has.
2. Egress — allowed by default, opt-out per repo
A consult sends the question and any packaged context to xAI — external egress.
Sharing code with the consulted model is allowed by default: a second model with
real context produces better opinions, so do not ask permission before a consult.
The exception is a repo that has opted out — if .cohort/project_context.md records
an egress restriction (client code, NDA, unreleased work), honor it absolutely
and consult only with fully abstracted questions or not at all. Never include
secrets, credentials, or .env contents in a consult prompt under any policy.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 85 lines · 35 tokens per session scan A afd1a65953ed
consult-grok is a command published in the GitHub repository askwigconsulting/cohort (2 stars, last pushed 28d ago), licensed MIT. It adds 35 tokens to every session and 987 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.