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-gptgit 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-gpt)<a href="https://agentmods.dev/commands/askwigconsulting/cohort/consult-gpt"><img src="https://agentmods.dev/badge/commands/askwigconsulting/cohort/consult-gpt.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 | $0.00038 | $0.01033 |
| Opus 5 | $0.00019 | $0.00517 |
| Sonnet 5 | $0.00008 | $0.00207 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
consult-gpt 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 — 94 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-gpt asks ChatGPT (through the OpenAI
Codex CLI running in a read-only sandbox) for an independent opinion on a hard problem —
a design choice, a tricky bug, a plan worth cross-examining. ChatGPT joins the office on
the office's terms: advisory only. It recommends; Claude weighs; the human decides.
1. Preflight — degrade gracefully
Check availability before promising anything:
codex login status
If the CLI is missing or not logged in, do not fail hard: say the consult is
unavailable, print the exact recovery steps
(npm install -g --prefix ~/.local @openai/codex, then codex login), answer from
your own analysis, and clearly label the answer as single-model.
Setup missing and model unavailable are different failures. If the CLI is set up but the flagship model itself is unavailable — usage limits reached, model errors that survive one retry — do not silently proceed and do not downgrade to a cheaper GPT. Ask the user how to proceed: wait and retry when the model is available again, or have Fable handle it single-model (labeled as such). The user picks; on "wait", agree a concrete retry point rather than blocking indefinitely.
2. Egress — allowed by default, opt-out per repo
A consult sends the question and any packaged context to OpenAI — 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.
3. Ask — package for disagreement
Run the consult with the sandbox pinned read-only — never workspace-write, never any
danger flag:
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 · 94 lines · 38 tokens per session scan A 21f618556605
consult-gpt is a command published in the GitHub repository askwigconsulting/cohort (2 stars, last pushed 28d ago), licensed MIT. It adds 38 tokens to every session and 1,033 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.