clarify

A guided command for resolving unclear parts of a project specification and updating the specification with agreed decisions. It can focus on areas such as security and can run in an autonomous mode.

In plain words
What is it for?
Use it to clarify a whole specification, focus on one category, or resolve open decisions in an autonomous review.
Why use it?
It reduces ambiguity before implementation by asking targeted questions and making recommendations. Saving each answer immediately helps preserve progress if the session stops.

Command for Claude Code

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 commands/ddunnock/claude-plugins/clarify
Clone the repo
git clone --depth 1 https://github.com/ddunnock/claude-plugins

Made for: Claude Code.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,629 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 $0.00012 $0.03629
Opus 5 $0.00006 $0.01814
Sonnet 5 $0.00002 $0.00726
Haiku 4.5 $0.00001 $0.00363

Measured 2d ago against content hash a14e632570d7, 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 2d 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.

mcps/knowledge-mcp/.claude/commands/clarify.md · 512 lines

How it starts

The opening of the file, as written. The whole thing — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clarify

SEAMS-enhanced ambiguity resolution with recommendations and immediate spec updates.

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).


Usage

/clarify                      # Start clarification session
/clarify spec.md              # Clarify specific spec
/clarify --category SECURITY  # Focus on specific category
/clarify --ralph              # Autonomous mode (ralph-loop enabled)

Session Constraints

  • Maximum 5 questions asked per interactive session
  • Maximum 10 questions total across all sessions for a spec
  • Never reveal queued questions in advance
  • Atomic save after each answer to prevent context loss

Memory Directives

Load these directive files for context-aware recommendations:

Always loaded:

  • constitution.md - Global principles, quality gates
  • security.md - Security requirements
  • testing.md - Test coverage requirements
  • documentation.md - Documentation standards

Project-specific (detected: Python ≥3.11, Poetry, MCP SDK):

  • python.md - Python standards, type hints, Pyright strict
  • git-cicd.md - Conventional commits, CI pipeline

SEAMS-Enhanced Taxonomy

Scan using this combined taxonomy. For each category, mark status: Clear / Partial / Missing.

Functional & Behavioral (Original + SEAMS)

Category Detection Focus Status Markers
SCOPE Feature boundaries, in/out declarations [TBD], "etc.", "might include"
BEHAVIOR User actions, state transitions "should", "might", "probably"
SEQUENCE Order of operations, workflows "before/after" ambiguity
AUTHORITY Decision makers, permissions, roles "someone", "appropriate person"

Data & Integration

Category Detection Focus Status Markers
DATA Entities, attributes, formats, validation Undefined formats, missing rules
INTERFACE API contracts, protocols, external deps Missing contracts, undefined protocols
CONSTRAINT Limits, bounds, technical constraints Undefined limits, implicit bounds
TEMPORAL Timing, duration, scheduling "soon", "quickly", "periodically"

Read the full file on GitHub · 512 lines

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. 2d ago First seen · 512 lines · 12 tokens per session scan A a14e632570d7

Subscribe to this mod's changes

clarify is a command published in the GitHub repository ddunnock/claude-plugins (12 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 3,629 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 2026-08-30.