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 fortunto2/solo-factory --skill domaingit clone --depth 1 https://github.com/fortunto2/solo-factoryWrote 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/fortunto2/solo-factory/domain)<a href="https://agentmods.dev/skills/fortunto2/solo-factory/domain"><img src="https://agentmods.dev/badge/skills/fortunto2/solo-factory/domain/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/fortunto2/solo-factory/domain"><img src="https://agentmods.dev/badge/skills/fortunto2/solo-factory/domain.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 | $0.00111 | $0.01575 |
| Opus 5 | $0.00056 | $0.00788 |
| Sonnet 5 | $0.00022 | $0.00315 |
| Haiku 4.5 | $0.00011 | $0.00158 |
Grade A, and why
solo-domain scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
avail() { [ "$(curl -sL -o /dev/null -w '%{http_code}' --max-time 20 \ How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
domain — is this name actually free?
A name is not available because a domain is free. It has to be clear on every surface the product will live on: the zones you will buy, the App Store (where names are unique and a collision blocks release), Google Play, the code host, and the trademark register. Checking only the domain is how people buy a domain for a name the App Store will later refuse.
Output: a table of candidates against those surfaces, and a recommendation that says what the runner-up trades away.
Workflow
- List candidates. 6–12 names, including the user's own suggestions verbatim — they know their brand voice, and the job here is verification, not taste.
- Zones. RDAP first, whois for ccTLDs — RDAP lies about them, see Gotchas.
- App Store. Exact-name search. Do this before pricing domains: a blocked store name makes the domain worthless.
- Code host. GitHub is a reliable signal; most social sites are not.
- Whatever sits on a taken
.com. Fetch its title. Parked junk, "Coming Soon" and a live business in the same category are three different risks, not one. - Trademark. Search the exact name plus "trademark". Flag holders who defend aggressively in that category.
- Recommend one, with the trade-off stated.
Zones
# RDAP: 404 = free, 200 = registered. -L is required — rdap.org answers 302 first.
avail() { [ "$(curl -sL -o /dev/null -w '%{http_code}' --max-time 20 \
"https://rdap.org/domain/$1")" = "404" ] && echo FREE || echo taken; }
# ccTLDs (.co .io .me .ai …) — RDAP usually has no server for them, so whois is the source.
avail_cc() { whois "$1" 2>/dev/null | grep -qiE "no match|not found|no data found" \
&& echo FREE || echo taken; }
Run the check against a domain known to be registered (google.com, google.co) before
trusting a batch. That one control call is what separates a report from a guess.
App Store
curl -s "https://itunes.apple.com/search?term=NAME&entity=software&limit=25&country=us" \
| python3 -c "
import json,sys,re
n='NAME'.lower()
r=json.load(sys.stdin)['results']
hit=[a['trackName'] for a in r if n==re.sub(r'[^a-z0-9]','',a['trackName'].lower().split(':')[0])]
print('TAKEN: '+hit[0] if hit else 'free')"
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.
- 10d ago First seen · 111 lines · 111 tokens per session scan A 1b8042c5b926
solo-domain is a skill published in the GitHub repository fortunto2/solo-factory (18 stars, last pushed today), licensed MIT. It adds 111 tokens to every session and 1,575 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
harness
Route Harness Starter Kit workflows. Use when the user invokes /harness with adopt, doctor, update, refresh, review, or review sub-agent, or asks to apply, diagnose, maintain, or review repository harness guidance.
product-diagnosis
Six-question diagnostic framework for G0 pre-check — validate product direction before development starts.
review
L1 internal review with auto-detection, design comparison, and Gate escalation path.
dev-plan
Generate a development plan with task breakdown and section 10 tracking tables.
knowledge-feedback
Scan child projects for pitfalls and propose company standard updates.
sop-review
A structured code-review procedure for checking a task against project rules and acceptance criteria. It loads the task, relevant standards, and the Git changes before reviewing every required checkpoint.