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 atretyak1985/swarmery --skill founder-reality-checkgit clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/founder-reality-check)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/founder-reality-check"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/founder-reality-check/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/atretyak1985/swarmery/founder-reality-check"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/founder-reality-check.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 | $0.00047 | $0.00631 |
| Opus 5.5 | $0.00019 | $0.00252 |
| Sonnet 5.5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
founder-reality-check 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
A VC's read on the project as it actually exists in the repo — copy, shipped surfaces, product state — against the business thesis. Direct, evidence-cited, read-only.
Stance
- Direct. No platitudes, no motivational language. Pass is the default verdict — the product earns "interesting" through evidence, not narrative.
- Disagree when the founder is wrong; a softened pass costs them months.
- Acknowledge limits: when you don't know a market, say so and say how to find out.
- End with the action to take this week, not a polite question.
Method
Read the repo's actual audience-facing surfaces (project.json → apps,
landing copy, product state) before judging anything. Evaluate the seven axes
— problem reality, market structure, founder–market fit, differentiation vs
moat, unit economics, why-now, one-business-or-two — each with evidence
(file paths, copy quotes, named competitors you searched for, not guessed).
Call out anti-patterns by name (AI-as-moat, TAM theater, idea-hopping, …).
Verdict: PASS | CONDITIONAL | PROMISING — where PASS means "kill or pivot".
A concept-conformance table (SHIPPED / PARTIAL / STUB / MISSING per promised
capability) grounds the marketing-vs-product gap.
Full axes, anti-pattern definitions, and output format:
resources/evaluation-axes.md.
How to use
What it does
Runs an investor-mode audit of the product: reads the shipped surfaces and copy, scores seven business axes with evidence, names the anti-patterns, and returns a blunt verdict with the one action to take this week. Read-only — it changes nothing.
When to use it
When the user explicitly asks for the business reality check — before a funding conversation, after a pivot, or when marketing and product may have drifted apart.
How to invoke
Load the skill and ask: "reality-check the product" or scope it: "reality-check the B2C funnel only". It reads project.json → apps and the repo's copy itself.
Worked example
On a repo shipping a B2B landing plus a consumer app: it reads both copies side by side, flags "one business or two?" hard, scores unit economics against the hardware CAC found in the pricing page, marks two promised capabilities STUB in the conformance table, and closes CONDITIONAL: "this week: pick the funnel; archive the other landing."
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 60 lines · 47 tokens per session scan A ed4c3bfb1265
founder-reality-check is a skill published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 631 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 2026-09-03.
Other skills, from other repositories
dependency-versions
MUST consult this skill before answering whenever the user's task involves external versioned dependencies — even if you think you can handle it directly. This applies to: checking if packages/tools are up to date, upgrading npm/pip/cargo/go dependencies, planning or writing CI/CD workflows (GitHub Actions, CircleCI…
finish
Ship phase — merge, PR, keep, or discard with pre-merge verification.
gws-quick-ref
Quick reference for gws CLI syntax — core patterns, key flags, pagination, field masks, and output formats.
excalidraw
Create or extend editable Excalidraw diagrams from descriptions or repository evidence using a local skeleton-to-scene converter.
style-ops
Maintain, validate or report on the Fakoli principles ledger, checking evidence pointers and keeping its Markdown projection synchronized.
gws-events-subscribe
Google Workspace Events: Subscribe to Workspace events and stream them as NDJSON.