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 ajhcs/mbse-agents --skill defense-founder-reviewgit clone --depth 1 https://github.com/ajhcs/mbse-agentsWrote 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/ajhcs/mbse-agents/defense-founder-review)<a href="https://agentmods.dev/skills/ajhcs/mbse-agents/defense-founder-review"><img src="https://agentmods.dev/badge/skills/ajhcs/mbse-agents/defense-founder-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/ajhcs/mbse-agents/defense-founder-review"><img src="https://agentmods.dev/badge/skills/ajhcs/mbse-agents/defense-founder-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 | $0.00048 | $0.03572 |
| Opus 5.5 | $0.00019 | $0.01429 |
| Sonnet 5.5 | $0.00010 | $0.00714 |
| Haiku 4.5 | $0.00005 | $0.00357 |
Grade A, and why
defense-founder-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 1mo 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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Defense Founder Review
Strategic review skill for defense, autonomy, and dual-use ventures. Applies a structured operating system -- capability gap analysis, incumbent failure mapping, vertical integration decisions, prototype planning, and honest moat assessment -- to every idea that passes through it.
This is a review process, not a persona. It clones an operating system: how to frame problems, what bets to prefer, what tradeoffs to reject, and what outputs to demand from a team.
Trigger Conditions
When to invoke
- User is evaluating a defense or dual-use startup idea
- User is turning a vague systems concept into a product company
- User is deciding what to vertically integrate vs outsource
- User is scoping an autonomy, robotics, sensor, or manufacturing platform
- User is reviewing whether a plan is ambitious enough for strategic relevance
- User asks for a "founder review" or "strategic review" of a defense/dual-use concept
When NOT to invoke
- Pure software SaaS with no hardware or physical-world component
- Academic research with no product intent
- Existing product iteration that does not need strategic reframing
- Consumer apps, social media, or adtech
- Problems where the physical world is not a binding constraint
The Kernel
Eight rules that define this skill's operating system. Every review applies all eight. When a rule is violated, name the violation explicitly.
Rule 1: Start from strategic need, not feature demand
The first question is not "what do users want?" The first question is: what capability gap exists, who cannot solve it today, and why the incumbent base is too slow, too fragmented, or too complacent.
Questions to ask:
- What mission or operational capability does not exist today?
- Who is the operator that cannot do their job because this does not exist?
- Why can't Lockheed, Raytheon, Northrop, L3Harris, or Palantir solve this?
- What structural constraint -- procurement speed, talent model, architecture choices -- makes the incumbent unable to respond?
- Is this a real gap or a procurement preference?
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.
- 1mo ago First seen · 357 lines · 48 tokens per session scan A 611a2412e116
defense-founder-review is a skill published in the GitHub repository ajhcs/mbse-agents (28 stars, last pushed 15d ago), licensed MIT. It adds 48 tokens to every session and 3,572 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
fs-notebook-tabs
A computer-science capstone: an on-device ML keyboard that predicts next words privately — problem, method, evaluation, and defense answers. Built as a decision-grade coursework defense deck for professor, defense committee.
html-ppt-zhangzara-pin-and-paper
A field-biology capstone on urban pollinator decline — the survey design, the data, the contribution, and the caveats. Built as a decision-grade coursework defense deck for faculty reviewers.
html-ppt-zhangzara-cartesian
An economics senior thesis on the employment effects of local minimum-wage increases — identification strategy, evidence, and limitations. Built as a decision-grade coursework defense deck for thesis committee.
html-ppt-zhangzara-scatterbrain
A design-school graduation project: a civic wayfinding system for a transit hub — the brief, the process, and the outcome. Built as a decision-grade coursework defense deck for crit panel, faculty.
deploying-ransomware-canary-files
Deploys and monitors ransomware canary files across critical directories using Python's watchdog library for real-time filesystem event detection. Places strategically named decoy files that mimic high-value targets (financial records, credentials, database exports) in locations ransomware typically enumerates first.…
aerospace-expert
Expert-level aerospace systems, flight management, maintenance tracking, aviation safety, and aerospace software. Use when the user mentions aviation, flight, maintenance, safety, or air traffic control, or when the task involves Aerospace Systems, Aviation Technologies, Standards and Regulations, or Flight Operations.