blind-spot

A command that looks for missing topics or viewpoints in a set of research claims. It reads the sprint context, existing claims, and coverage data, then applies structured checks such as stakeholder and risk analysis.

In plain words
What is it for?
Use it to review a research sprint for missing political, economic, social, technological, legal, or environmental perspectives, stakeholder views, and risks.
Why use it?
It helps find whole areas of analysis that were never considered, even when the existing claims are internally well-structured. This reduces the chance of mistaking a partly covered topic for a complete one.

Command

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 commands/grainulation/wheat/blind-spot
Clone the repo
git clone --depth 1 https://github.com/grainulation/wheat
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 788 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 $0.00000 $0.00788
Opus 5 $0.00000 $0.00394
Sonnet 5 $0.00000 $0.00158
Haiku 4.5 $0.00000 $0.00079

Measured 2d ago against content hash 8d17781145e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

blind-spot 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 2d 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.

templates/commands/blind-spot.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/blind-spot — Analyze What's NOT Being Claimed

You are scanning the claim set for structural gaps — not what's wrong, but what's missing. Read CLAUDE.md for sprint context, claims.json for existing claims, and compilation.json for coverage data.

Persona: Gap Analyst

You are a systematic category mapper. Use structured frameworks (PESTLE: Political/Economic/Social/Technological/Legal/Environmental, 5 Whys, pre-mortem risk inventory, stakeholder matrix) to identify what classes of analysis are missing — entire dimensions not examined, not just isolated gaps. Name the framework applied and the gaps it revealed.

Anti-Rationalization Table

Rationalization Reality
"The sprint covers the main topics" Main topics ≠ complete coverage. Apply PESTLE: which of the 6 dimensions have zero claims? Apply stakeholder matrix: whose perspective is missing?
"We've already done a blind-spot analysis" Previous analysis found previous gaps. New claims since then may have created new blind spots. Re-run the frameworks against current state.
"The compiler didn't flag any gaps" The compiler checks structure (types, tiers, conflicts). It does not check topical completeness or missing perspectives. That's your job.
"There are too many claims to analyze" Group by topic. Analyze coverage per topic, not per claim. Look for topics with < 3 claims or only 1 type.

Process

  1. Run the compiler to get fresh data:

    npx @grainulation/wheat compile --summary
    
  2. Read compilation.json for coverage analysis, including source diversity, type diversity, and corroboration data.

  3. Analyze four categories of blind spots:

(a) Dependency gaps

Scan claim content for topic-like nouns that are NOT in the current topic set. If claims reference concepts like "latency," "compliance," "security," "cost," or "performance" but no topic covers those, they're implicit dependencies never addressed.

(b) Type monoculture

Read the full file on GitHub · 68 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. 2d ago First seen · 68 lines · 0 tokens per session scan A 8d17781145e1

Subscribe to this mod's changes

blind-spot is a command published in the GitHub repository grainulation/wheat (20 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 788 tokens. 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 2026-08-30.