clarification-protocol

A question-asking process for resolving important uncertainties before implementing software changes.

In plain words
What is it for?
It is for confirming database structure, required and optional relationships, audit fields, report columns, row meanings, grouping, and output formats before work begins.
Why use it?
It prevents assumptions about data fields, relationships, statuses, reports, and file formats that can cause expensive redesigns later.

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/gosha70/code-copilot-team/clarification-protocol
Clone the repo
git clone --depth 1 https://github.com/gosha70/code-copilot-team

Made for: Cursor.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,686 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 $0.00020 $0.01686
Opus 5 $0.00010 $0.00843
Sonnet 5 $0.00004 $0.00337
Haiku 4.5 $0.00002 $0.00169

Measured yesterday against content hash 1f58b5012d78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clarification-protocol 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 yesterday.

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.

adapters/cursor/.cursor/rules/clarification-protocol.mdc · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clarification Protocol

Rules for when to ask clarifying questions instead of making assumptions.

Always Ask Before Implementing

Data Model Decisions

Before creating or modifying entity fields, confirm with the user:

  • Field granularity: Single combined field vs split into components? (e.g., one field vs multiple for compound values)
  • Normalization: Flat fields on the parent entity vs a separate related entity?
  • Status/type fields: Enum values — which states are needed? Will they change over time?
  • Relationships: One-to-many vs many-to-many? Optional vs required?
  • Audit fields: Which standard fields? (createdAt, updatedAt, deletedAt, createdBy?)

Don't assume the simplest representation. Compound fields that seem fine early often need to be split later for filtering, sorting, or reporting.

Output Format Decisions

Before generating reports, exports, or formatted output:

  • Column names: Confirm exact headers (e.g., "Count" vs "Total" vs "Amount").
  • Row structure: What does each record represent (per day? per item? per transaction?)?
  • Grouping: How should data be aggregated?
  • File format: CSV, JSON, PDF, or in-app table?

Generating the wrong format costs a full rebuild. Asking costs one message.

UI Layout Decisions

Before implementing visual components:

  • Image positioning: Left/right of text? Above/below? Full-width banner?
  • Section ordering: What content is above the fold? What can the user scroll to?
  • Interactive elements: Buttons, toggles, dropdowns — confirm behavior on click.
  • Responsive behavior: Mobile-first or desktop-first? What collapses on small screens?

Auth & Access Decisions

Before implementing authentication or authorization:

  • Auth strategy: Password-based? Magic link? OAuth? Passkeys?
  • Who can access what: Admin-only sections? Guest access? Role-based?
  • Account requirement: Is registration mandatory or optional?
  • Session behavior: How long should sessions last? Remember me?

Read the full file on GitHub · 161 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. yesterday First seen · 161 lines · 20 tokens per session scan A 1f58b5012d78

Subscribe to this mod's changes

clarification-protocol is a cursor rule published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 1,686 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.