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/yoichiojima-2/consultant/consultgit clone --depth 1 https://github.com/yoichiojima-2/consultantWrote 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/yoichiojima-2/consultant/consult)<a href="https://agentmods.dev/commands/yoichiojima-2/consultant/consult"><img src="https://agentmods.dev/badge/commands/yoichiojima-2/consultant/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 | $0.00009 | $0.00415 |
| Opus 5 | $0.00005 | $0.00208 |
| Sonnet 5 | $0.00002 | $0.00083 |
| Haiku 4.5 | $0.00001 | $0.00042 |
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.
What it actually says
Act as an engagement manager at a top consulting firm. Work the problem below through the complete consulting flow defined in the consulting skill (see ${CLAUDE_PLUGIN_ROOT}/skills/consulting/SKILL.md and the category files it references).
Problem: $ARGUMENTS
If no problem was provided above, ask for one and stop.
Follow this process, showing your work at each step:
- Clarify scope — Restate the problem. If critical context is missing (industry, timeframe, success criteria, constraints), ask up to 3 clarifying questions before proceeding. If the user gave enough context, state your assumptions explicitly and continue.
- Day-1 hypothesis — State your initial answer based on the situation as given.
- Define the problem (SCQ) — Situation, Complication, Question.
- Structure (Issue Tree) — Break the question into a MECE issue tree, 2–3 levels deep. Render it as an ASCII diagram.
- Prioritize (80/20) — Identify the 2–3 branches that likely drive most of the answer and say why you're deprioritizing the rest.
- Analyze — Work the priority branches. Select 1–3 frameworks from the skill that fit (e.g., Profitability, Porter's 5 Forces, Value Chain) — do not apply frameworks that don't earn their place. Quantify wherever possible; state assumptions for every number.
- Synthesize — For each analysis, extract the "So what?".
- Recommend (Pyramid Principle) — Lead with the answer in one sentence, then 3–5 supporting arguments with evidence, then risks and next steps.
End by offering to produce a deliverable from ${CLAUDE_PLUGIN_ROOT}/skills/consulting/templates/ (e.g., business case, SWOT report, project charter) if one fits.
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 · 24 lines · 9 tokens per session scan A 71829b87a5f4
consult is a command published in the GitHub repository yoichiojima-2/consultant (41 stars, last pushed 16d ago), licensed MIT. It adds 9 tokens to every session and 415 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
save
Save this conversation as a new or existing reusable context.
wp-polylang
Translate an existing WordPress site into a second language using Polylang.