blindspot-pass

blindspot-pass is a skill for Claude Code, Codex from orenluxy/fable-method. It costs 95 tokens per session (806 once invoked), scanned A, original, MIT.

A pre-work scan that looks for important questions the user may not know to ask. It examines the relevant code, outside services, and practical constraints before implementation.

In plain words
What is it for?
Use it before a substantial task to identify unknowns, risks, dependencies, and questions that should be resolved first.
Why use it?
It reduces surprises caused by vague requirements, unfamiliar technology, hidden conventions, or missing checks.

Skill for Claude CodeCodex

Part of the fable-method plugin — 8 skills, 2 agents, 3 hooks 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 skills/orenluxy/fable-method/blindspot-pass
Any agent
npx skills add orenluxy/fable-method --skill blindspot-pass
Clone the repo
git clone --depth 1 https://github.com/orenluxy/fable-method

Made for: Claude Code, Codex.

Or install fable-method, the plugin that ships this one along with the rest of its 8 skills, 2 agents, 3 hooks.

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 blindspot-pass

README.md
[![agentmods](https://agentmods.dev/badge/skills/orenluxy/fable-method/blindspot-pass.svg)](https://agentmods.dev/skills/orenluxy/fable-method/blindspot-pass)
Your own site
<a href="https://agentmods.dev/skills/orenluxy/fable-method/blindspot-pass"><img src="https://agentmods.dev/badge/skills/orenluxy/fable-method/blindspot-pass.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 806 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 $0.00095 $0.00806
Opus 5 $0.00048 $0.00403
Sonnet 5 $0.00019 $0.00161
Haiku 4.5 $0.00010 $0.00081

Measured 3d ago against content hash 1d8e5e305335, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

blindspot-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 3d 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.

skills/blindspot-pass/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Blindspot Pass

Purpose: close the gap between the map (the user's prompt) and the territory (the codebase / real-world constraints) before any implementation happens. The output is NOT a plan — it is a ranked list of unknowns the user didn't know they had.

Procedure

  1. Establish the user's starting point. If not already stated, ask ONE question: "What's your experience level with this domain and this codebase area?" Their answer calibrates everything below. Do not skip this — a blindspot pass for an expert and a novice are different documents.

  2. Scan the territory. Before writing anything, actually investigate:

    • If subagents are available, delegate this step to the territory-scout agent (haiku) with a one-paragraph brief: the task, what to look for, output format. This is the model-economy rule — scanning is mechanical, keep it off the expensive model. Tell the user in one line that you're doing so.
    • Search the relevant parts of the codebase (existing conventions, similar features, config, tests).
    • Search the web if the domain involves external APIs, libraries, pricing, or anything that changes over time.
    • Check for constraints the user didn't mention: auth, rate limits, data formats, deployment environment, existing migrations.
    • Analysis and ranking of the findings stay with YOU (the main model) — the scout gathers facts only.
  3. Classify what you find using the four quadrants:

    • Known knowns — explicit in the user's request. List briefly to confirm shared understanding.
    • Known unknowns — things the user flagged as open. Propose how to resolve each.
    • Unknown knowns — things the user almost certainly has opinions about but didn't state (naming conventions, error-handling style, UI taste, tolerance for dependencies). Turn each into a direct question.
    • Unknown unknowns — constraints or landmines the user hasn't considered at all. This is the main value of the pass.
  4. Rank by cost-of-late-discovery. Order every item by how expensive it would be to discover it mid-implementation or after merge. A wrong architecture assumption ranks above a naming question.

Read the full file on GitHub · 38 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. 3d ago First seen · 38 lines · 95 tokens per session scan A 1d8e5e305335

Subscribe to this mod's changes

blindspot-pass is a skill published in the GitHub repository orenluxy/fable-method (1 stars, last pushed 27d ago), licensed MIT. It adds 95 tokens to every session and 806 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

glossary-init

USE WHEN setting up a repo for AI-first work, when an agent hallucinates domain term meaning, or when user asks to bootstrap / extend the repo's domain glossary. Surfaces candidate terms by identifier frequency, asks the user for 1-sentence definitions, writes GLOSSARY.md at repo root. Idempotent — re-running adds new…

Filip-Podstavec/claude-leverage · 119 tokens

codex-pair-resume

Resume codex-pair for this project after a previous pause. Removes .codex-pair/state/paused and clears failure state. Review resumes on the next supported file edit; missing state is a no-op.

Lykhoyda/ask-llm · 51 tokens

generate-tests

Generate unit tests for a .NET service following the coverage-kit conventions. Use when the user asks to 'generate tests', 'backfill tests', 'characterize this service', or 'add tests for' a target after coverage-init has run. Operates in characterization mode (freeze current behavior for existing code) or spec mode…

livlign/claude-skills · 179 tokens

conventions-init

USE WHEN setting up a repo for AI-first work (after /init-repo), or when the context-surface hook should start feeding repo conventions to agents before edits. Drafts conventions.yml at repo root: per-kind casing (inferred from the code), a vague-name denylist seed, directory roles, and a hand-filled house-rules…

Filip-Podstavec/claude-leverage · 124 tokens

opik

This skill should be used when the user needs to add Opik tracing or integrations to their code, instrument an LLM application, or needs reference for Opik SDK usage (Python, TypeScript, REST API). Use for tasks like "add tracing", "instrument my code", "use trackopenai", "add OpikTracer", "what span types are…

comet-ml/opik-claude-code-plugin · 84 tokens

codex-review

Get a second opinion from OpenAI Codex on your current code changes. Analyzes staged/unstaged diffs and returns prioritized findings. Use when user asks to "review with Codex", "Codex code review", or "ask Codex to check my code".

Lykhoyda/ask-llm · 60 tokens