speckit.clarify

speckit.clarify is a skill for Claude Code, Codex from wedabro/bro-skills. It costs 19 tokens per session (420 once invoked), scanned A, original, MIT.

A specification review that finds unclear or conflicting requirements before implementation. It checks vague wording, missing limits, undefined error behavior, and unclear user roles.

In plain words
What is it for?
Use it to review a feature specification, ask up to three important clarification questions, correct minor wording issues, and mark the specification as clarified after the answers are incorporated.
Why use it?
It prevents developers from building on assumptions that could change the design or produce different interpretations of the same request.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to review a feature specification, ask up to three important clarification questions, correct minor wording issues, and mark the specification as clarified after the answers are incorporated.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wedabro/bro-skills/speckit.clarify
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.

Any agent
npx skills add wedabro/bro-skills --skill speckit.clarify
Clone the repo
git clone --depth 1 https://github.com/wedabro/bro-skills

Made for: Claude Code, Codex.

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 speckit.clarify

README.md
[![agentmods](https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.clarify/github.svg)](https://agentmods.dev/skills/wedabro/bro-skills/speckit.clarify)
Your own site
<a href="https://agentmods.dev/skills/wedabro/bro-skills/speckit.clarify"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.clarify/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for speckit.clarify

Your own site · 80×15
<a href="https://agentmods.dev/skills/wedabro/bro-skills/speckit.clarify"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.clarify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 420 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00019 $0.00420
Opus 5 $0.00010 $0.00210
Sonnet 5 $0.00004 $0.00084
Haiku 4.5 $0.00002 $0.00042

Measured 10d ago against content hash 539cda2b783f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

speckit.clarify 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 10d 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/skills/speckit.clarify/SKILL.md · 43 lines

What it actually says

🎯 Mission

Scan spec.md → detect ambiguity → ask developer up to 3 questions → update spec.

📥 Input

  • .agents/specs/[feature]/spec.md

📋 Protocol

  1. Scan spec.md to find:
    • Vague language: "fast", "many", "easy to use", "similar", "etc."
    • Missing boundaries: Unknown min/max, pagination limits, file size limits
    • Undefined error handling: What happens when X fails?
    • Ambiguous actors: Who is "User"? Admin? Guest? Registered?
  2. Categorize each issue:
    • 🔴 CRITICAL: Architectural influence, MUST ask developer
    • 🟡 IMPORTANT: Should ask but can suggest default
    • 🟢 MINOR: Editorial correction that cannot change behavior, such as a typo, broken reference, or inconsistent requirement ID.
  3. Ask the developer MAXIMUM 3 CRITICAL questions, each question has an options table:
Option Describe Impact
A ... ...
B ... ...
C ... ...
4. Auto-fix only behavior-neutral 🟢 MINOR items. Present missing limits,
permissions, defaults, and error behavior as assumptions or questions; do
not write them into the spec without approval.
5. Update spec.md with clarifications → mark `[CLARIFIED]` .

## 📤 Output
- File: Updated `.agents/specs/[feature]/spec.md`

## 🚫 Guard Rails
- MAXIMUM 3 questions — don't ask too many.
- DO NOT change the original intent of the spec.
- DO NOT invent product limits, permissions, defaults, or acceptance criteria.
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. 10d ago First seen · 43 lines · 19 tokens per session scan A 539cda2b783f

Subscribe to this mod's changes

speckit.clarify is a skill published in the GitHub repository wedabro/bro-skills (2 stars, last pushed 14d ago), licensed MIT. It adds 19 tokens to every session and 420 once invoked, about $0.0001 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.