Consult

What it does

When your agent uses it

• Reviewing specs
• Implementations
• PRs with external models
• Running parallel 3-way reviews (cmap)

Example prompts

• “/consult”

Requirements

• A credential in CLAUDE_CODE_OAUTH_TOKEN
• A credential in ANTHROPIC_AUTH_TOKEN

What it can do on your machine

Read from SKILL.md and the folder at commit 9cd8607. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • CLAUDE_CODE_OAUTH_TOKEN
  • ANTHROPIC_AUTH_TOKEN
  • ANTHROPIC_API_KEY
  • CODEX_API_KEY
  • OPENAI_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Consult loads about 1.1k tokens when it runs. Until then it costs about 91 tokens; SKILL.md has 276 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~91

When it runs · the whole SKILL.md, loaded when a task matches

~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:27

  ## Credentials and `.env`

• NoteMentions a .env fileSKILL.md:29

  `consult` loads `<workspace>/.env` and sets every key the shell does not already define, **credentials included**. Those

• NoteMentions a .env fileSKILL.md:34

  UDE] auth: CLAUDE_CODE_OAUTH_TOKEN (from .env)`. If a review fails with a usage-limit or auth error while your own login

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from cluesmith/codev at commit 9cd8607, republished under its Apache-2.0 licence (© cluesmith). 276 words, ~1,066 tokens.

name

consult

description

AI consultation CLI — query Gemini, Codex, or Claude for reviews and analysis. ALWAYS check this skill before running any `consult` command. Use when reviewing specs, plans, implementations, or PRs with external models, running parallel 3-way reviews (cmap), or checking consultation stats. The `-m` model flag is always required except for `consult stats`.

consult -m <model> [options]
consult stats [options]

-m, --model <model>         Model to use (required except stats)
--prompt <text>              Inline prompt (general mode)
--prompt-file <path>         Prompt file path (general mode)
--protocol <name>            Protocol: spir, aspir, air, bugfix, maintain
-t, --type <type>            Review type (see below)
--issue <number>             Issue number (required in architect context)
--output <path>              Save result to file
--plan-phase <phase>         Scope review to a plan phase (porch use)
--context <path>             Context file with feedback (porch use)
--project-id <id>            Project ID for metrics (porch use)
--days <n>                   Stats: limit to last N days (default: 30)
--project <id>               Stats: filter by project ID
--last <n>                   Stats: show last N invocations
--json                       Stats: output as JSON

consult -m gemini --prompt "What's the best way to structure auth?"
consult -m codex --prompt-file review-checklist.md

consult -m gemini --type spec --issue 42
consult -m codex --type plan --issue 42
consult -m claude --type integration --issue 42

consult -m gemini --type integration --issue 42 --output /tmp/cmap-gemini-42.md &
consult -m codex --type integration --issue 42 --output /tmp/cmap-codex-42.md &
consult -m claude --type integration --issue 42 --output /tmp/cmap-claude-42.md &
wait

consult stats                     # 30-day summary
consult stats --days 7 --json     # Last 7 days as JSON
consult stats --project 42        # Filter by project

© cluesmith, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .codex/skills/consult of cluesmith/codev.

Open the folder on GitHubat commit 9cd8607