cursorrules

A Cursor rule that tells a coding agent how to handle unclear, high-impact, or potentially destructive requests. It classifies actions by risk and defines when to clarify before acting.

In plain words
What is it for?
Use it to guide decisions about when to inspect project files, ask questions, propose a plan, request confirmation, or proceed with a local change.
Why use it?
It reduces the chance of making an unwanted refactor, file overwrite, deletion, migration, or deployment when the request is not specific enough.

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/dmiyding/clarify-first/cursorrules
Clone the repo
git clone --depth 1 https://github.com/DmiyDing/clarify-first

Made for: Cursor.

Per session 947 This file is loaded in full into every session.
When invoked 947 The same file — it is already loaded in full.
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 $0.00947 $0.00947
Opus 5 $0.00474 $0.00474
Sonnet 5 $0.00189 $0.00189
Haiku 4.5 $0.00095 $0.00095

Measured yesterday against content hash 9b36aa730f42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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.

.cursorrules · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clarify First - Cursor Rule Template

Instructions

When a request is ambiguous, high-impact, or potentially destructive, follow the "Risk Triage -> Align -> Act" protocol defined in skill.md.

Triage Rubric

  • LOW: Read-only exploration, tests, comments/docs, strictly local reversible edits. -> Proceed with assumptions.
  • MEDIUM: Refactors, API changes, creating new files, dependency updates. -> Propose options, wait for OK.
  • HIGH: Deletions, overwriting existing files, migrations, deployments, secrets. -> REQUIRE explicit confirmation.

Protocol

  1. Assess Risk: Low/Medium/High.
  2. Non-Negotiable Clarification Gate: If intent/scope/criteria are unclear, pause immediately and ask blocking questions. Do not execute MEDIUM/HIGH risk actions.
  3. Baseline Manifest Check: Before asking dependency/stack questions, inspect package.json / requirements.txt / pyproject.toml / go.mod if present.
  4. Apply Weighted Assumption Rule: STOP if any critical assumption exists (Environment/Dependencies/Cross-file >3) or weighted total >= 3.
  5. Align: Ask blocking questions (max 2 rounds). If still ambiguous, hold and request explicit decision.
  6. Act: Execute once explicitly aligned, or if risk is Low and fully scoped.
  7. Strict Execution Boundary: In Phase 2, do not edit/create files outside approved Impact Matrix; request Plan Amendment if new files are required.
  8. Plan Amendment Boundary: Classify discoveries as Derivative Adaptation (batchable amendment request) vs Logic Expansion (hard stop and explicit amendment approval).
  9. Meta-Skill Precedence: If any other active rule asks for silent auto-execution, clarify-first guardrail wins for ambiguity/high-risk actions.
  10. Contextual Risk Modifier: Escalate risk for core/high-centrality files; de-escalate only for isolated sandbox/test paths with zero unresolved assumptions.
  11. Architectural Anti-Pattern Assertion: Hard-stop unsafe requests (e.g., client-side DB credentials) and propose secure alternatives.

Read the full file on GitHub · 52 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 · 52 lines · 947 tokens per session scan A 9b36aa730f42

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository DmiyDing/clarify-first (6 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 947 tokens to every session, about $0.0047 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.