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.
git clone --depth 1 https://github.com/sageox/oxWrote 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/commands/sageox/ox/session-start)<a href="https://agentmods.dev/commands/sageox/ox/session-start"><img src="https://agentmods.dev/badge/commands/sageox/ox/session-start/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/commands/sageox/ox/session-start"><img src="https://agentmods.dev/badge/commands/sageox/ox/session-start.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 | $0.00000 | $0.00261 |
| Opus 5.5 | $0.00000 | $0.00104 |
| Sonnet 5.5 | $0.00000 | $0.00052 |
| Haiku 4.5 | $0.00000 | $0.00026 |
Grade A, and why
session-start 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.
What it actually says
Start recording this agent session to the project ledger.
Use when:
- Beginning a new coding session you want captured
- Starting work on a feature, bug fix, or investigation worth recording
- You want decisions and context preserved for teammates
- Resuming work after a break and want to record the new session
Keywords: session start, record, capture, begin, log, track, ledger, start recording
Common Issues
Already recording
Symptom: session already active or similar error
Solution: A session is already in progress. Run ox agent <id> session stop first if you need to restart
No agent detected
Symptom: Agent ID is missing or unrecognized
Solution: Run ox agent prime first to register this agent instance
Not initialized
Symptom: No SageOx configuration found
Solution: Run ox init to initialize SageOx in this repository
Post-Command: Show Notice (REQUIRED)
After the command completes, check the JSON output for a notice field.
If present, you MUST display the notice text to the user verbatim. This is a one-time
transparency notice about session recording that the user needs to see.
$ox agent session start
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 · 32 lines · 0 tokens per session scan A b1e68f3b2727
session-start is a command published in the GitHub repository sageox/ox (65 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 261 tokens. 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 commands, from other repositories
brainstorm
A retired command for generating ideas before implementation. Its description says to use the Superpowers brainstorming skill instead.
setup-mcp-claude-code
Build and register the Contorium MCP server for Claude Code or Cursor Agent.
1-plan
Plans a thread and generates thread-specific spec documents.
0-setup
Scaffolds the project and sets up the Kamma environment.
4-finalize
Finalizes a reviewed thread, updates project documentation, and handles cleanup.
loop
Plans a standing loop thread for repeated cycles of work.