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/machinewisdomai/fava-trails/consultgit clone --depth 1 https://github.com/MachineWisdomAI/fava-trailsWrote 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/machinewisdomai/fava-trails/consult)<a href="https://agentmods.dev/commands/machinewisdomai/fava-trails/consult"><img src="https://agentmods.dev/badge/commands/machinewisdomai/fava-trails/consult.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 5.1 | $0.00000 | $0.01398 |
| Opus 5 | $0.00000 | $0.00699 |
| Sonnet 5 | $0.00000 | $0.00280 |
| Haiku 4.5 | $0.00000 | $0.00140 |
Grade A, and why
consult 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 6d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
consult - AI Consultation CLI
The consult command provides a unified interface for AI consultation with external models (Gemini, Codex, Claude). It operates in three modes: general (ad-hoc prompts), protocol-based (structured reviews), and stats.
Synopsis
consult -m <model> [options]
consult stats [options]
Required Option
-m, --model <model> Model to use (required for all modes except stats)
Models
| Model | Alias | Backend | Notes |
|---|---|---|---|
gemini |
pro |
gemini-cli | File access via --yolo, fast |
codex |
gpt |
@openai/codex | Read-only sandbox, thorough |
claude |
opus |
Claude Agent SDK | Balanced analysis with tool use |
Modes
General Mode
Send an ad-hoc prompt to a model.
# Inline prompt
consult -m gemini --prompt "What's the best way to structure auth middleware?"
# Prompt from file
consult -m codex --prompt-file review-checklist.md
Options:
--prompt <text>— Inline prompt text--prompt-file <path>— Read prompt from a file
Cannot combine --prompt with --prompt-file or --type.
Protocol Mode
Run structured reviews tied to a development protocol (SPIR, TICK, bugfix, maintain).
# Review a spec (auto-detects project context in builder worktrees)
consult -m gemini --protocol spir --type spec
# Review a plan
consult -m codex --protocol spir --type plan
# Review implementation
consult -m claude --protocol spir --type impl
# Review a PR
consult -m gemini --protocol spir --type pr
# Phase-scoped review (builder context only)
consult -m codex --protocol spir --type phase
# Integration review
consult -m gemini --type integration
Options:
--protocol <name>— Protocol: spir, bugfix, tick, maintain-t, --type <type>— Review type: spec, plan, impl, pr, phase, integration--issue <number>— Issue number (required from architect context)
Context resolution:
- Builder context (cwd inside
.builders/): auto-detects project ID, spec, plan, and PR from porch state - Architect context (cwd outside
.builders/or--issueprovided): requires--issue <N>to identify the project
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.
- 6d ago First seen · 201 lines · 0 tokens per session scan A 5c19efc3d6cf
consult is a command published in the GitHub repository MachineWisdomAI/fava-trails (25 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,398 tokens. 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 2026-08-30.
Other commands, from other repositories
rebase
Fast-forward or rebase the current worktree's branch onto main. Deterministic script for the clean path; LLM steps in only to resolve real conflicts or ask you.
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.