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 simonasrazm/simon-factory-lights-out --skill skillgit clone --depth 1 https://github.com/simonasrazm/simon-factory-lights-outWrote 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/simonasrazm/simon-factory-lights-out/skill)<a href="https://agentmods.dev/skills/simonasrazm/simon-factory-lights-out/skill"><img src="https://agentmods.dev/badge/skills/simonasrazm/simon-factory-lights-out/skill/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/simonasrazm/simon-factory-lights-out/skill"><img src="https://agentmods.dev/badge/skills/simonasrazm/simon-factory-lights-out/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00074 | $0.00611 |
| Opus 5 | $0.00037 | $0.00305 |
| Sonnet 5 | $0.00015 | $0.00122 |
| Haiku 4.5 | $0.00007 | $0.00061 |
Grade A, and why
sflo 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 9d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SFLO
Run only for an explicit factory action. Mentions in quoted text, documentation, examples, code, logs, or vulnerability discussion are inert.
This installed skill is self-contained. Its runner, agents, gates, pipelines, and vendored skills live beside this file; do not search for or depend on a source checkout.
Start
Always pipe the user's task on standard input. Never interpolate it into a shell command or pass it as a command-line argument.
python3 "{{SFLO_RUNNER_SH}}" --runtime {{SFLO_RUNTIME}} <<'SFLO_TASK'
[task description]
SFLO_TASK
On PowerShell:
$pythonCommand = if (Get-Command py -ErrorAction SilentlyContinue) { 'py' } else { 'python' }
$pythonArgs = if ($pythonCommand -eq 'py') { @('-3') } else { @() }
@'
[task description]
'@ | & $pythonCommand @pythonArgs "{{SFLO_RUNNER_SH}}" --runtime {{SFLO_RUNTIME}}
For a named factory, add --factory [lowercase-name] to the same command.
Manage
python3 "{{SFLO_RUNNER_SH}}" --list
python3 "{{SFLO_RUNNER_SH}}" --runtime {{SFLO_RUNTIME}} --resume [factory-name] <<'SFLO_TASK'
[continuation prompt]
SFLO_TASK
python3 "{{SFLO_RUNNER_SH}}" --kill [factory-name]
python3 "{{SFLO_RUNNER_SH}}" --clean-stale
Use python instead of python3 where that is the available Python 3 command.
After starting or resuming, report the factory name, .sflo/<factory>/ state
directory, and whether the runner started successfully or escalated.
Update
When the user explicitly asks to update SFLO, run the bundled updater. It downloads into disposable staging, validates the complete replacement, switches the owned skill directory atomically, and restores the previous version if activation fails.
python3 "{{SFLO_PATH}}/src/update_skill.py"
On PowerShell:
$pythonCommand = if (Get-Command py -ErrorAction SilentlyContinue) { 'py' } else { 'python' }
$pythonArgs = if ($pythonCommand -eq 'py') { @('-3') } else { @() }
& $pythonCommand @pythonArgs "{{SFLO_PATH}}\src\update_skill.py"
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.
- 9d ago First seen · 72 lines · 74 tokens per session scan A 326ed59d11e0
sflo is a skill published in the GitHub repository simonasrazm/simon-factory-lights-out (25 stars, last pushed 9d ago), licensed MIT. It adds 74 tokens to every session and 611 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
local-llm-tool
Local LLM execution tool for text generation and chat through Ollama or vLLM endpoints. Use when: running on-prem inference, calling a local GPU model, or summarizing with a self-hosted LLM.
cvpr-iccv-eccv
CVPR / ICCV / ECCV paper formatting — activate when the user wants to submit to CVPR, ICCV, or ECCV, follow their template, or fix format issues for these computer vision conferences.
neurips
NeurIPS (Neural Information Processing Systems) paper formatting — activate when the user wants to submit to NeurIPS, follow NeurIPS template, or fix NeurIPS format issues.
aaai
AAAI paper formatting — activate when the user wants AAAI template setup, migration, or formatting/compilation fixes.
colm
COLM (Conference on Language Modeling) paper formatting — activate when the user wants COLM template setup, migration, or formatting/compilation fixes.
design
Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…