clarify-first

clarify-first is a cursor rule for Cursor from madebyaris/cursor-composer-rules. It costs 21 tokens per session (785 once invoked), scanned A, original, MIT.

A set of rules for asking clarifying questions only when the intended result remains unclear after inspecting the project.

In plain words
What is it for?
It is for handling ambiguous coding tasks, especially when repository files, tests, configuration, or recent changes can answer the question.
Why use it?
It reduces interruptions while keeping questions tied to decisions that would materially change the work.

Cursor rule for Cursor

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 rules/madebyaris/cursor-composer-rules/clarify-first
Clone the repo
git clone --depth 1 https://github.com/madebyaris/cursor-composer-rules

Made for: Cursor.

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-first

README.md
[![agentmods](https://agentmods.dev/badge/rules/madebyaris/cursor-composer-rules/clarify-first.svg)](https://agentmods.dev/rules/madebyaris/cursor-composer-rules/clarify-first)
Your own site
<a href="https://agentmods.dev/rules/madebyaris/cursor-composer-rules/clarify-first"><img src="https://agentmods.dev/badge/rules/madebyaris/cursor-composer-rules/clarify-first.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 785 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 $0.00021 $0.00785
Opus 5 $0.00010 $0.00392
Sonnet 5 $0.00004 $0.00157
Haiku 4.5 $0.00002 $0.00078

Measured 4d ago against content hash 0cd0226ae4dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clarify-first 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.

.cursor/rules/clarify-first.mdc · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clarify first

Questions interrupt and cost trust. Default: infer the intent, state the assumption in one line, act. Ask only when confusion weight is high. Same gate as composer-core § Confusion weight — keep them in sync.

Plan mode exception

In plan mode, structured questions belong in the plan (assumptions, design forks, open questions). That is the deliverable, not stalling. After the plan is confirmed, return to infer-and-act for implementation.

Default: inspect, then infer

Most ambiguity dissolves on inspection. Before asking, check:

  • Repo structure, manifests, configs
  • Existing tests and fixtures — they encode intent
  • Recent commits and PRs in the area
  • README, ADRs, comments, how similar features were built

If the answer is in the codebase, find it. Then infer:

  • Constraints already given → proceed. Don't bounce a detailed prompt back as questions; act and state assumptions inline.
  • X-Y problem → reconcile. Name the gap in one line and offer the better path — more useful than silently building Y or stalling.

Inference stands on cues in the request and the code — not vibes.

Confusion weight

Use the Low / Medium / High table in composer-core § Confusion weight — keep that table authoritative; do not fork a second copy here.

High only when at least one is true:

  1. Irreversible or destructive — data loss, hard delete, force-push-class ops, irreversible migrations
  2. Contract-changing — schema, auth model, public API shape, persisted formats
  3. Contradictory cues — request or thread conflicts with itself or with clear repo signal
  4. No repo signal and guessing wrong would waste real work or harm correctness

If none apply, do not ask — decide or assume-and-act.

Ask when — and only when

Ask 1–2 questions, in one round, when all are true:

  1. Confusion weight is high
  2. The answer materially changes what you'll build
  3. The answer cannot be inferred from inspection

Read the full file on GitHub · 86 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 · 86 lines · 21 tokens per session scan A 0cd0226ae4dc

Subscribe to this mod's changes

clarify-first is a cursor rule published in the GitHub repository madebyaris/cursor-composer-rules (3 stars, last pushed 16d ago), licensed MIT. It adds 21 tokens to every session and 785 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.