blind-spot-pass

blind-spot-pass is a skill for Claude Code, Cursor from emaraschio/cursor-commands. It costs 138 tokens per session (2,350 once invoked), scanned A, original, MIT.

A pre-build review that compares the user's plan with the actual project and sorts missing information into four kinds of known and unknown gaps.

In plain words
What is it for?
Use it to identify missing requirements and answer high-value questions before building; it produces a review first and waits for permission to execute.
Why use it?
It reveals hidden assumptions about dependencies, edge cases, and the possible impact of changes before implementation begins.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: user-invocable in frontmatter, but also installed under .cursor/.

Good fit Use it to identify missing requirements and answer high-value questions before building; it produces a review first and waits for permission to execute.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/emaraschio/cursor-commands/blind-spot-pass
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.

Any agent
npx skills add emaraschio/cursor-commands --skill blind-spot-pass
Clone the repo
git clone --depth 1 https://github.com/emaraschio/cursor-commands

Made for: Claude Code, 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 blind-spot-pass

README.md
[![agentmods](https://agentmods.dev/badge/skills/emaraschio/cursor-commands/blind-spot-pass/github.svg)](https://agentmods.dev/skills/emaraschio/cursor-commands/blind-spot-pass)
Your own site
<a href="https://agentmods.dev/skills/emaraschio/cursor-commands/blind-spot-pass"><img src="https://agentmods.dev/badge/skills/emaraschio/cursor-commands/blind-spot-pass/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for blind-spot-pass

Your own site · 80×15
<a href="https://agentmods.dev/skills/emaraschio/cursor-commands/blind-spot-pass"><img src="https://agentmods.dev/badge/skills/emaraschio/cursor-commands/blind-spot-pass.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,350 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00138 $0.02350
Opus 5 $0.00069 $0.01175
Sonnet 5 $0.00028 $0.00470
Haiku 4.5 $0.00014 $0.00235

Measured 10d ago against content hash 4b8c2fb5fc0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

blind-spot-pass 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 10d 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/skill-contracts/blind-spot-pass/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Blind spot pass

Role

You run a blind spot pass before building. The user gives a rough plan, goal, or prompt; you treat it as the map and the real project as the territory. You classify what is known and unknown across four quadrants, then ask the highest-leverage interview questions so building does not start on hidden assumptions.

This skill uses a two-step handshake: (1) deliver the pass and wait for pass approval; (2) build only after a later explicit execute now (or equivalent), or when the user explicitly says to skip the pass and build now. Pass approval is not build. This skill is plan-only on delivery and on pass approval.

When to use

Use before writing, coding, product specs, or any build where the prompt may be incomplete. Run this when the user wants to find unknowns or surface unstated context before the agent acts. For a greenfield fog map with parallel tracks, use pathfinder. For a six-part delegation contract, use define-agent-goal. For a runnable prompt, use structure-prompt. For a technical audit of a step-by-step implementation plan, use a dedicated plan-preflight skill, not this one.

Intensity

Intensity When
standard (default) Always, unless the user requests red-team
red-team Only when the user asks to challenge, break, or red-team the plan

There is no light mode. Detection phrases for red-team include: challenge, break, red-team, red team, find why this fails, stress-test the ask.

Under red-team, still deliver the four-quadrant pass and interview questions. Actively seek reasons the map (ask) fails, and push harder on §4 sub-bullets and high-leverage questions. Do not replace the pass with a free-form principal-engineer risk report or a step-by-step plan audit (that is plan-preflight skill work).

Workflow

Run phases in order. Do not deliver the pass until Phase 3. Do not execute the task, scaffold code, or run destructive commands when delivering the pass, when the user only approves the pass, or unless the user explicitly says to skip the pass and build now.

Read the full file on GitHub · 152 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 152 lines · 138 tokens per session scan A 4b8c2fb5fc0a

Subscribe to this mod's changes

blind-spot-pass is a skill published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 1mo ago), licensed MIT. It adds 138 tokens to every session and 2,350 once invoked, about $0.0007 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.