clarify

clarify is a skill for Claude Code, Codex from ramboz/jig. It costs 153 tokens per session (4,274 once invoked), scanned A, original, MIT.

A structured scan for unclear or incomplete parts of a project specification.

In plain words
What is it for?
Use it to check scope, acceptance criteria, dependencies, non-functional requirements, edge cases, and terminology, then add prioritized questions to the specification.
Why use it?
It finds ambiguities before implementation or review, reducing the risk that developers interpret requirements differently.

Skill for Claude CodeCodex

Part of the jig plugin — 20 skills 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 skills/ramboz/jig/clarify
Any agent
npx skills add ramboz/jig --skill clarify
Clone the repo
git clone --depth 1 https://github.com/ramboz/jig

Made for: Claude Code, Codex.

Or install jig, the plugin that ships this one along with the rest of its 20 skills.

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 clarify

README.md
[![agentmods](https://agentmods.dev/badge/skills/ramboz/jig/clarify.svg)](https://agentmods.dev/skills/ramboz/jig/clarify)
Your own site
<a href="https://agentmods.dev/skills/ramboz/jig/clarify"><img src="https://agentmods.dev/badge/skills/ramboz/jig/clarify.svg" alt="Measured on agentmods" height="20"></a>
Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,274 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 $0.00153 $0.04274
Opus 5 $0.00077 $0.02137
Sonnet 5 $0.00031 $0.00855
Haiku 4.5 $0.00015 $0.00427

Measured 4d ago against content hash 89d0fc1e7d50, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

hosts/claude/skills/clarify/SKILL.md · 392 lines

How it starts

The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec 023 introduces this skill as jig's pre-spec ambiguity scan. It is the sixth non-stub active jig skill that ships without a .py helper — clarify is fundamentally a judgment skill, and the determinism it needs (locate the target doc, find an existing ## Clarifications section if any, append new entries) Claude can run inline via Read + Edit. The skill slots between workflow.py new <slug> (stub reservation) and the READY_FOR_REVIEW transition (spec body ready for first review).

Per user direction on 2026-05-18, jig's clarify ships as a standalone baseline, not a deferral surface. Power users who want spec-kit's /speckit.clarify install spec-kit and invoke it explicitly under /speckit.*. There is no category-based deferral hint in this skill's description.

What this skill does

Runs a structured ambiguity scan against a DRAFT-state spec document across six categories aligned with jig's slice template (Scope & Boundaries / Acceptance Criteria Testability / Dependencies & Blockers / Non-functional Requirements / Edge Cases & Failure Modes / Terminology Consistency). The skill rates each category Clear / Partial / Missing, selects up to five prioritized questions (Partial/Missing weighted above Clear), asks them one at a time recording the user's verbatim answer, and appends a ## Clarifications section to the target document with the Q/A entries plus a coverage summary table.

The skill is breadth over depth: catch the obvious unanswered questions across the six taxonomy categories in a few minutes, leave deep domain-specific clarification (legal review, regulatory edges, multi-stakeholder facilitation) to the dev's judgment or to a richer team process. The five-question budget exists to keep the scan lightweight enough to actually run before each READY_FOR_REVIEW transition — not so heavy it becomes a chore the team skips.

When to use vs. when to defer

There are four sibling skills people often confuse with this one. Pick the right one:

Read the full file on GitHub · 392 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 392 lines · 153 tokens per session scan A 89d0fc1e7d50

Subscribe to this mod's changes

clarify is a skill published in the GitHub repository ramboz/jig (6 stars, last pushed 3d ago), licensed MIT. It adds 153 tokens to every session and 4,274 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

motherduck-build-cfa-app

Design a MotherDuck-backed customer-facing analytics app. Use for embedded analytics, multi-tenant SaaS reporting, or product analytics for external users -- whenever the decision depends on per-customer isolation, backend routing, service-account boundaries, read scaling, or Hypertenancy-style patterns.

motherduckdb/agent-skills · 63 tokens

motherduck-build-dashboard

Build a live MotherDuck dashboard as a Dive. Use when composing one shareable KPI, trend, and breakdown story over existing MotherDuck data, especially when the result should stay a saved workspace artifact rather than a full application.

motherduckdb/agent-skills · 50 tokens

motherduck-build-data-pipeline

Design an end-to-end MotherDuck data pipeline. Use for ETL/ELT workflows -- choosing raw, staging, and analytics boundaries, bulk ingestion paths, transformation sequencing, dlt/dbt integration, publication targets, or whether DuckLake is actually required.

motherduckdb/agent-skills · 59 tokens

motherduck-connect

Connect to MotherDuck from any application. Use when setting up database connectivity via the Postgres endpoint (recommended), pgduckdb, native DuckDB API, or JDBC. Covers connection strings, authentication, SSL, and environment variable configuration.

motherduckdb/agent-skills · 52 tokens

motherduck-create-dive

Create, edit, manage, share, or embed MotherDuck Dives — live React + SQL dashboards, charts, and data apps saved in the workspace. Use for any dashboard, chart, KPI display, or data visualization over MotherDuck data, and for Dive authoring mechanics such as getdiveguide, useSQLQuery, local preview, version history…

motherduckdb/agent-skills · 95 tokens

motherduck-create-flight

Create, schedule, run, and debug MotherDuck Flights — Python jobs that run on MotherDuck compute. Use whenever someone wants to create a flight, schedule a Python script or recurring job on MotherDuck, set up scheduled ingestion from Postgres, dlt sources, S3, BigQuery, Snowflake, or APIs, refresh aggregates or…

motherduckdb/agent-skills · 106 tokens