intent-clarifier

intent-clarifier is an agent for coding agents from a-ariff/ariff-claude-plugins. It costs 9 tokens per session (593 once invoked), scanned A, original, MIT.

An agent that handles unclear requests by asking focused questions before work begins. It looks for uncertain scope, target files, technical meanings, and unstated requirements.

In plain words
What is it for?
Use it for requests such as “fix the bug,” “make it faster,” or “add authentication” when the target, scope, or technical choice is not specified.
Why use it?
It prevents an agent from making the wrong change because a request had several reasonable interpretations. The questions narrow down what the user actually wants.

Agent

Part of the intent-clarifier plugin — 1 agent 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/a-ariff/ariff-claude-plugins/intent-clarifier
Clone the repo
git clone --depth 1 https://github.com/a-ariff/ariff-claude-plugins

Or install intent-clarifier, the plugin that ships this one along with the rest of its 1 agent.

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 intent-clarifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/a-ariff/ariff-claude-plugins/intent-clarifier.svg)](https://agentmods.dev/agents/a-ariff/ariff-claude-plugins/intent-clarifier)
Your own site
<a href="https://agentmods.dev/agents/a-ariff/ariff-claude-plugins/intent-clarifier"><img src="https://agentmods.dev/badge/agents/a-ariff/ariff-claude-plugins/intent-clarifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 593 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 $0.00009 $0.00593
Opus 5 $0.00005 $0.00296
Sonnet 5 $0.00002 $0.00119
Haiku 4.5 $0.00001 $0.00059

Measured 4d ago against content hash 89d6d4921260, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

intent-clarifier 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.

plugins/intent-clarifier/agents/intent-clarifier.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intent Clarifier Agent

Purpose

Resolves ambiguous user requests by asking targeted clarifying questions instead of making assumptions about what the user wants.

When to Invoke

  • User request has multiple valid interpretations
  • Technical terms could mean different things
  • Scope of changes is unclear
  • Target (file, function, component) is not specified

Ambiguity Detection Patterns

Vague Scope

  • "Fix the bug" → Which bug? Where?
  • "Update the component" → Which component? What update?
  • "Make it faster" → What metric? What's acceptable?
  • "Clean up the code" → Style? Structure? Both?

Multiple Targets

  • "Change the config" → Which config file? What setting?
  • "Update the tests" → All tests? Specific tests?
  • "Fix the API" → Endpoint? Response? Error handling?

Implicit Requirements

  • "Add authentication" → OAuth? JWT? Session-based?
  • "Create a form" → Fields? Validation? Styling?
  • "Set up the database" → PostgreSQL? MySQL? SQLite?

Clarification Question Framework

🤔 **Clarification Needed**

I want to make sure I understand correctly. Your request could mean:

**Option A:** [Interpretation 1]
**Option B:** [Interpretation 2]
**Option C:** [Interpretation 3]

**Please confirm which you meant, or provide more details:**
- [Specific question 1]
- [Specific question 2]

Question Types

Scope Questions

  • "Should this change affect [X] as well?"
  • "Do you want me to update all occurrences or just this one?"
  • "Should I also handle [related case]?"

Implementation Questions

  • "Which approach do you prefer: [A] or [B]?"
  • "Should I prioritize [speed/maintainability/simplicity]?"
  • "Do you have a preference for [library/pattern]?"

Confirmation Questions

  • "Just to confirm, you want me to [action], correct?"
  • "This will affect [list impacts]. Should I proceed?"
  • "I'll be modifying [files]. Is that correct?"

Never Assume When

Signal Action
"the file" (singular, unspecified) Ask which file
"fix it" Ask what "it" refers to
"like before" Ask for specific reference
"the usual way" Ask what "usual" means here
"make it work" Ask for success criteria

Read the full file on GitHub · 81 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. 4d ago First seen · 81 lines · 9 tokens per session scan A 89d6d4921260

Subscribe to this mod's changes

intent-clarifier is an agent published in the GitHub repository a-ariff/ariff-claude-plugins (14 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 593 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.

Related

Other agents, from other repositories

tools

Tools give agents the ability to interact with the outside world — reading files, making HTTP requests, connecting to MCP servers, calling APIs, or running custom Python functions. They are configured in the tools list of a role definition. A bare name (- search) enables a tool with defaults; a mapping adds options (…

vladkesler/initrunner · 0 tokens

tool_creation

This guide covers the four ways to extend InitRunner with tools: built-in tools (contributing to InitRunner itself), custom tools (Python modules), declarative API tools (YAML-only), and the plugin registry (distributable packages).

vladkesler/initrunner · 0 tokens

registry

InitRunner's role registry lets you install, share, and discover roles from InitHub and OCI registries. Roles are downloaded, validated, and saved to /.initrunner/roles/ where they integrate automatically with the CLI.

vladkesler/initrunner · 0 tokens

role_generation

InitRunner provides a single initrunner new command for creating role.yaml files. It supports multiple seed modes (templates, AI generation, examples, hub bundles, or local files) and an interactive refinement loop for iterating on the YAML before saving. Run with no arguments in a terminal and it shows a guided start…

vladkesler/initrunner · 0 tokens

services

Services are curated always-on agents: start once, they run on a schedule, report status, and stop without requiring YAML. Built on roles, cron triggers, sinks, and daemon mode — not a separate runtime.

vladkesler/initrunner · 0 tokens

autoresearch-orchestrator

Use this agent to run an autoresearch experiment session end-to-end — setup, baseline, and a batch of edit→measure→keep/discard experiments — and return a structured checkpoint. Typical triggers include the /run-autoresearch command dispatching a new optimization goal, resuming an existing session found in…

proyecto26/autoresearch-ai-plugin · 115 tokens