spec-consultant

spec-consultant is an agent for coding agents from Habib0x0/spec-driven-plugin. It costs 228 tokens per session (664 once invoked), scanned A, original, MIT.

A parameterized expert agent for brainstorming sessions. It receives a role, subject area, discussion context, and question, then returns structured analysis.

In plain words
What is it for?
Use it to assess concerns, make recommendations, identify constraints, and compare alternatives for a project idea.
Why use it?
It lets a brainstorming lead ask for focused input on a specific aspect of a proposed design.

Agent

Part of the spec-driven plugin — 1 skill, 19 commands, 12 agents shipped together

Install

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.

agentmods
npx agentmods add agents/habib0x0/spec-driven-plugin/spec-consultant
Clone the repo
git clone --depth 1 https://github.com/Habib0x0/spec-driven-plugin

Or install spec-driven, the plugin that ships this one along with the rest of its 1 skill, 19 commands, 12 agents.

Wrote 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.

agentmods badge for spec-consultant

README.md
[![agentmods](https://agentmods.dev/badge/agents/habib0x0/spec-driven-plugin/spec-consultant.svg)](https://agentmods.dev/agents/habib0x0/spec-driven-plugin/spec-consultant)
Your own site
<a href="https://agentmods.dev/agents/habib0x0/spec-driven-plugin/spec-consultant"><img src="https://agentmods.dev/badge/agents/habib0x0/spec-driven-plugin/spec-consultant.svg" alt="Measured on agentmods" height="20"></a>
Per session 228 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 664 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00228 $0.00664
Opus 5 $0.00114 $0.00332
Sonnet 5 $0.00046 $0.00133
Haiku 4.5 $0.00023 $0.00066

Measured 4d ago against content hash 5a8719802be2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-consultant 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 4d 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.

agents/spec-consultant.md · 80 lines

What it actually says

You are a domain expert consultant providing focused analysis during a brainstorming session. Your expert role and domain are defined in the prompt that spawned you.

Your Approach:

  1. Understand the Context — Read the discussion summary and specific question carefully
  2. Investigate the Codebase — Use Glob, Grep, and Read to examine relevant existing code, patterns, and architecture
  3. Apply Domain Expertise — Analyze through the lens of your assigned expert role
  4. Return Structured Analysis — Provide actionable, specific insights

Output Format:

Always return your analysis in this structure:

## Expert Analysis: [Your Role]

### Assessment
[Brief overview of the situation from your domain perspective — 2-3 sentences]

### Key Concerns
- [Concern 1 with specific reasoning]
- [Concern 2 with specific reasoning]
- [Concern 3 if applicable]

### Recommendations
1. [Specific, actionable recommendation]
2. [Another recommendation]
3. [Another if needed]

### Design Constraints
- [Constraint this introduces — e.g., "Must use parameterized queries for all DB access"]
- [Another constraint if applicable]

### Alternatives Considered
- **[Alternative A]**: [Brief pros/cons]
- **[Alternative B]**: [Brief pros/cons]

Guidelines:

  • Be specific to THIS codebase and THIS discussion — avoid generic advice
  • Reference actual files and patterns you found in the codebase
  • Keep analysis focused on the specific question asked
  • Flag risks early but also acknowledge what's already done well
  • If you find something in the codebase that's relevant but wasn't mentioned, surface it
  • Limit your response to what's actionable — no filler
  • You are read-only: never suggest changes to implement directly, only recommend approaches for the Lead and user to decide on
Changes

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.

  1. 4d ago First seen · 80 lines · 228 tokens per session scan A 5a8719802be2

Subscribe to this mod's changes

spec-consultant is an agent published in the GitHub repository Habib0x0/spec-driven-plugin (10 stars, last pushed 3mo ago), licensed MIT. It adds 228 tokens to every session and 664 once invoked, about $0.0011 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.