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 ARCASSystems/FounderOS --skill blind-spot-reviewgit clone --depth 1 https://github.com/ARCASSystems/FounderOSWrote 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/arcassystems/founderos/blind-spot-review)<a href="https://agentmods.dev/skills/arcassystems/founderos/blind-spot-review"><img src="https://agentmods.dev/badge/skills/arcassystems/founderos/blind-spot-review/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/arcassystems/founderos/blind-spot-review"><img src="https://agentmods.dev/badge/skills/arcassystems/founderos/blind-spot-review.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 | $0.00061 | $0.01042 |
| Opus 5 | $0.00030 | $0.00521 |
| Sonnet 5 | $0.00012 | $0.00208 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
blind-spot-review 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blind-Spot Review
Runs on: reasoning - reads your files and reasons; any capable agent can run this.
The first draft of an advisory deliverable is rarely the safe final draft. This skill runs a second pass against nine fixed categories so the founder can decide what to add, what to accept, and what to leave out.
When To Run
- A proposal, brief, playbook, meeting-prep note, client update, or decision document has a complete first draft.
- The founder asks what is missing.
- A deliverable is about to run through
pre-send-check. - The stakes include external trust, legal exposure, financial terms, client expectations, or relationship damage.
Inputs Required
- Path to the deliverable.
- Source material used to create it: transcript, notes, client context, prior decision, or brief.
- The external party or audience.
- Intended send channel and date, if known.
If any input is missing, stop and name the gap. Do not review a deliverable without source context.
The Nine Categories
For each category, mark ADDRESSED, GAP, or NOT APPLICABLE with a one-line reason.
1. Legal and IP Status
Check ownership, licenses, registrations, names, contracts, claims, and any rights the deliverable assumes.
2. Contracts In Flight
Check pending proposals, signed contracts, vendor terms, partner terms, employment or contractor terms, and anything that changes if the advice is followed.
3. Creditor and Payment Positions
Check unpaid invoices, loans, deposits, deferred pay, refund exposure, or anyone who must be paid before value is split.
4. Community and Data Assets
Check audiences, email lists, CRM records, customer data, content libraries, social accounts, group chats, and consent boundaries.
5. Relationship Externalities
Check co-founders, team members, family, friends, partners, investors, and anyone whose position changes because of the recommendation.
6. Regulatory and Timing Issues
Check renewal dates, tax dates, filing deadlines, permit windows, launch dates, meeting dates, campaign timing, or any dated constraint.
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 · 104 lines · 61 tokens per session scan A eb3444be2799
blind-spot-review is a skill published in the GitHub repository ARCASSystems/FounderOS (5 stars, last pushed 27d ago), licensed MIT. It adds 61 tokens to every session and 1,042 once invoked, about $0.0003 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
wiki-ingest
Compile a raw source (document, URL content, meeting notes, research output) into a wikikit agent wiki — merge-don't-overwrite, log contradictions, maintain cross-references, then lint. Use whenever the user says "add this to the wiki", "ingest this", or drops new source material for a wiki maintained with…
publish-report
Publish local HTML, Markdown, or built static web projects with Pagecast as shareable public URLs. Use whenever Codex creates or finishes an .html, .htm, .md, .markdown, or static build output that a person could share (a report, plan, doc, dashboard, or analysis) — proactively offer to publish it without being asked…
alive-search
Search across all walnuts -- decisions, people, files, references, insights, log history.
alive-inbox
Scan 03Inbox/ for unrouted files, present routing suggestions.
alive-people
Weekly -- cross-reference people mentions, nudge stale contacts.
founder-voice
Founder voice enforcement for all written output. Apply to any text another person will read.