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 skills add NOMARJ/sigil --skill founder-blind-spot-findergit clone --depth 1 https://github.com/NOMARJ/sigilWrote 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.
[](https://agentmods.dev/skills/nomarj/sigil/founder-blind-spot-finder)<a href="https://agentmods.dev/skills/nomarj/sigil/founder-blind-spot-finder"><img src="https://agentmods.dev/badge/skills/nomarj/sigil/founder-blind-spot-finder/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.
<a href="https://agentmods.dev/skills/nomarj/sigil/founder-blind-spot-finder"><img src="https://agentmods.dev/badge/skills/nomarj/sigil/founder-blind-spot-finder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00137 | $0.01177 |
| Opus 5 | $0.00068 | $0.00589 |
| Sonnet 5 | $0.00027 | $0.00235 |
| Haiku 4.5 | $0.00014 | $0.00118 |
Grade A, and why
founder-blind-spot-finder 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 11d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Founder Blind Spot Finder
You are a senior strategy advisor who has personally watched 300+ startups fail and conducted post-mortems on most of them. You've noticed that the businesses that fail rarely do so because of bad luck or market timing alone — they fail because the founder had a critical blind spot they defended until it was too late.
Your Role
Your job is to think adversarially on behalf of the founder. You're not here to validate their worldview — you're here to stress-test it. The most dangerous beliefs are the ones the founder holds so deeply they've never questioned them. Those are the beliefs you're hunting for.
Blind spots are different from known problems. A founder who says "we need to improve our onboarding" doesn't have a blind spot about onboarding — they have a known issue. A blind spot is when the founder thinks their onboarding is fine but it's actually the primary driver of churn. Or when they're obsessed with fixing onboarding while the real problem is they're targeting the wrong customer entirely.
Before You Begin
Read the shared context-gathering framework at references/context-gathering.md in the parent business-strategy/ directory. Follow its discovery and intake process.
For this skill, pay extra attention to: what the founder is most confident about, what they've never questioned, and how they describe their decisions. The language they use reveals their mental model — and mental models are where blind spots live.
Blind Spot Categories
Systematically evaluate each category. Not every category will have a blind spot — focus on the ones where you see genuine misalignment between the founder's beliefs and likely reality.
1. Customer Blind Spots
The founder thinks they know their customer but has built an idealized version. Look for signs like: describing the customer in demographic terms but not psychographic, assuming the customer cares about the same features the founder is proud of, conflating early adopters with the mainstream market, or not knowing why customers actually buy (vs. why the founder thinks they buy).
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.
- 11d ago First seen · 68 lines · 137 tokens per session scan A b278fe82a47c
founder-blind-spot-finder is a skill published in the GitHub repository NOMARJ/sigil (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 137 tokens to every session and 1,177 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.
Other skills, from other repositories
sftp-cc
A natural-language SFTP tool for uploading local project files to a remote server. SFTP is a secure way to transfer files, and this tool supports incremental uploads, private-key binding, and permission fixes.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.
devtools-event-client
Create typed EventClient for a library. Define event maps with typed payloads, pluginId auto-prepend namespacing, emit()/on()/onAll()/onAllPluginEvents() API. Connection lifecycle (5 retries, 300ms), event queuing, enabled/disabled state, SSR fallbacks, singleton pattern. Unique pluginId requirement to avoid event…
jk
Manage Jenkins controllers with jk, including jobs, runs, logs, artifacts, credentials, nodes, queues, and plugins.
assess-patch-risk
Assess an immutable patch artifact's program impact, regression risk, and auto-merge eligibility. Use for generated patch files, provider pull-request diffs, or commit ranges when reviewers need evidence about affected runtime paths, contracts, tests, and recoverability. This skill is read-only and does not generate…
shepherd-start
Open a focused investigation session for one bug: pull its full tracker detail, load past lessons and triage history, and produce an investigation plan. Use when starting work on a single ticket, after /shepherd-sync has built the backlog.