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.
npx agentmods add commands/nicoladevera/thinking-stack/blindspotgit clone --depth 1 https://github.com/nicoladevera/thinking-stackWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00014 | $0.01982 |
| Opus 5 | $0.00007 | $0.00991 |
| Sonnet 5 | $0.00003 | $0.00396 |
| Haiku 4.5 | $0.00001 | $0.00198 |
Grade A, and why
blindspot 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.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blindspot — Gap Analysis for Ideas and Thinking
You are running a blindspot audit: a structured analysis that surfaces what's missing from both the idea itself and the thinking behind it. Your role is not to evaluate whether the idea is good or bad — it is to map what's outside the current frame: unexplored assumptions, absent perspectives, unexamined dimensions, and cognitive patterns that may be shaping what gets seen and what doesn't.
The user invoked this with: $ARGUMENTS
Phase 1: Intake & Readiness
Assess whether $ARGUMENTS gives you something to audit. The bar is low — you need: (1) something to examine (an idea, plan, decision, problem framing, or question), and (2) enough context to understand the domain and what the user is trying to do. Vague or early-stage input is fine; even an undeveloped idea has a frame that can be audited.
If the input is too thin (no discernible idea, domain, or direction):
Use AskUserQuestion to ask 1–2 targeted clarifying questions. Only ask what's actually missing:
- What are you thinking about — what's the idea, decision, or question you want to audit?
- What's the decision or outcome at stake, if any?
If the input is ready: proceed directly.
Once you have enough context, synthesize a Subject Statement — 1 sentence stating exactly what's being audited. Use AskUserQuestion to present it and ask the user to confirm it accurately captures what they want audited. Wait for explicit confirmation before proceeding. If they correct or refine it, update accordingly.
Phase 2: Research (Optional, Targeted)
Determine whether external grounding would surface gaps that analysis alone would miss: competitive context, analogous situations, domain base rates, known failure modes, or relevant precedents the user may not have considered.
If yes: run 2–3 targeted WebSearch / WebFetch queries. Surface relevant findings in a brief paragraph before analysis begins. Focus on:
- How similar ideas have played out in analogous contexts
- Known blind spots or failure patterns in this domain
- External factors (market, regulatory, competitive) that frequently go unexamined in this type of decision
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.
- 2d ago First seen · 171 lines · 14 tokens per session scan A 51d98e0a2e7f
blindspot is a command published in the GitHub repository nicoladevera/thinking-stack (2 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 1,982 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.
Other commands, from other repositories
change
Entry point for any change request. Orchestrates the planner-routing pipeline (cm-planner → executor → reviewer → conventions-audit → test-author → commit). Use for any work that touches code or docs.
tree
Show file tree with sync status indicators showing which files are indexed, modified, new, or deleted.
adr
You are helping create a new ADR (Architecture Decision Record). This is a conversational process — you interview the user about the decision, then create a filled-in record. ADRs capture the WHY behind technical choices so future-you understands the reasoning.
routine
Execute one maintenance routine defined in scv/routines/ .md (task + guardrails + exit-criteria contract), or list defined routines. SCV never schedules — pair with host features like /loop or cron yourself. Use whenever the user asks to run a recurring maintenance task, or asks what routines exist — not only when…
tldr
Re-apply TLDR rules for this turn (verdict first, no filler).
guide
Interactive guide to fellowship. Walks you through a real task using the structured research-plan-implement flow, then shows you what's next.