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 alex-jb/solo-founder-os --skill sfos-splunk-obsgit clone --depth 1 https://github.com/alex-jb/solo-founder-osWrote 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/alex-jb/solo-founder-os/sfos-splunk-obs)<a href="https://agentmods.dev/skills/alex-jb/solo-founder-os/sfos-splunk-obs"><img src="https://agentmods.dev/badge/skills/alex-jb/solo-founder-os/sfos-splunk-obs/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/alex-jb/solo-founder-os/sfos-splunk-obs"><img src="https://agentmods.dev/badge/skills/alex-jb/solo-founder-os/sfos-splunk-obs.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 | $0.00136 | $0.01285 |
| Opus 5 | $0.00068 | $0.00642 |
| Sonnet 5 | $0.00027 | $0.00257 |
| Haiku 4.5 | $0.00014 | $0.00128 |
Grade A, and why
sfos-splunk-obs 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 12d 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.
description: Ship reflections, eval drift, and bandit regret from the solo-founder-os 11-agent stack into Splunk over HEC. Five-minute install, zero new Python deps (stdlib urllib + json + sqlite3), six-panel dashboard y How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sfos-splunk-obs
Splunk adapter for solo-founder-os — the 11-agent autonomous stack a single founder uses to run a company.
LangSmith and Phoenix are designed for synchronous request-response agents. SFOS-obs is for the other shape: long-running cron-scheduled file-based agents that reflect on themselves and learn. This skill emits the three streams that matter — agent outcomes, eval drift, bandit regret — into Splunk over HEC.
When to use this skill
Invoke this skill whenever the user:
- Runs solo-founder-os (or any SFOS agent) on cron / launchd and wants observability
- Asks "are my agents learning or just running"
- Reports a skill quietly regressing on its own eval set
- Wants to see bandit regret per marketing arm
- Wants the SFOS reflections / evals / bandit streams to land in the same Splunk index as their server logs
- Sets up dashboards for SFOS — import
dashboard.xmland the six panels populate within one sweep
Do NOT invoke for short-lived synchronous agent observability (LangSmith / Phoenix fit that shape better), for hosted SaaS APM (Datadog / HyperDX), or when the user does not already have a Splunk Cloud / Enterprise stack.
Three streams, three sourcetypes
| Sourcetype | Source | What it answers |
|---|---|---|
sfos:reflection |
~/.<agent>/reflections.jsonl |
What did each agent try to do, and did it work? |
sfos:eval |
~/.solo-founder-os/evals/*.json |
Is any skill silently regressing? |
sfos:bandit |
~/.marketing_agent/history.db |
Which marketing arms is the bandit learning are best? |
Five-minute install
-
Sign up for Splunk Cloud free tier and enable an HEC token (Settings → Data Inputs → HTTP Event Collector → New Token, sourcetypes
sfos:reflection,sfos:eval,sfos:bandit). -
Set two env vars:
export SPLUNK_HEC_URL="https://<your-stack>.splunkcloud.com:8088" export SPLUNK_HEC_TOKEN="<paste-token>" -
Run one sweep to verify connectivity:
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.
- 12d ago First seen · 88 lines · 136 tokens per session scan A 6d30533784ef
sfos-splunk-obs is a skill published in the GitHub repository alex-jb/solo-founder-os (11 stars, last pushed 2mo ago), licensed MIT. It adds 136 tokens to every session and 1,285 once invoked, about $0.0007 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
c-schedule
Smart scheduling — automate recurring Claude tasks with cost control. Deliver results to Telegram, file, or notification. Built into OpenPaw.
c-cron
Manage cron jobs and macOS launchctl services — schedule recurring tasks, start/stop services using lunchy-go.
api-interface-design
Use when designing public APIs, module boundaries, provider adapters, tool schemas, or data contracts.
explore
Explore the codebase and summarize how the project is wired.
cron
A guide to Cron, a Unix system that runs commands automatically at scheduled times. It explains crontab files, which store those schedules, along with time formats, service management, logs, and troubleshooting.
graphify
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…