agentx: Command for Claude Code

.claude/commands/ox-session-stop.md

ox-session-stop is a command for Claude Code from sageox/agentx. It costs 0 tokens per session (373 once invoked), scanned C, original, MIT.

A command for stopping an ox CLI session recording and saving the session to the project ledger. Afterward, it may require generating and pushing a summary from the raw session file.

In plain words
What is it for?
Use it when ending a recorded ox agent session and when the command output asks you to create or push a summary.
Why use it?
It preserves the session record and provides recovery guidance if the richer summary step fails.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Codex.

This is sageox/agentx's own configuration. It tells Claude Code how to work on agentx itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentx configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sageox/agentx. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sageox/agentx/main/.claude/commands/ox-session-stop.md
Clone the repo
git clone --depth 1 https://github.com/sageox/agentx

Made for: Claude Code.

Wrote 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.

agentmods badge for ox-session-stop

README.md
[![agentmods](https://agentmods.dev/badge/commands/sageox/agentx/ox-session-stop/github.svg)](https://agentmods.dev/commands/sageox/agentx/ox-session-stop)
Your own site
<a href="https://agentmods.dev/commands/sageox/agentx/ox-session-stop"><img src="https://agentmods.dev/badge/commands/sageox/agentx/ox-session-stop/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.

agentmods 80×15 button for ox-session-stop

Your own site · 80×15
<a href="https://agentmods.dev/commands/sageox/agentx/ox-session-stop"><img src="https://agentmods.dev/badge/commands/sageox/agentx/ox-session-stop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 373 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00373
Opus 5.5 $0.00000 $0.00149
Sonnet 5.5 $0.00000 $0.00075
Haiku 4.5 $0.00000 $0.00037

Measured 1mo ago against content hash 5ec48b8a9f97, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

ox-session-stop scanned grade C 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 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- Keep this file thin. Behavioral guidance (use-when, common-issues, errors) belongs in the ox CLI JSON output (guidance field), not here. Skills are agent-specific wrappers; ox serves all agents (Codex, etc.). Except
.claude/commands/ox-session-stop.md · 28 lines

What it actually says

Stop recording and save this agent session to the project ledger.

Post-Command: Generate and Push Summary (REQUIRED)

After the command completes, check the JSON output for guidance and summary_prompt fields. Follow the guidance field for next steps. The summary step is critical for session completeness.

If summary_prompt is present:

  1. Read the prompt carefully — it references the raw session file on disk
  2. Read the raw session file at the path specified in the prompt
  3. Generate the summary JSON following the Output Format in the prompt
  4. Save it to a temporary file (e.g., .ox-summary.json in the workspace root, or /tmp/ox-summary.json) — do NOT write to the session cache dir as it may be outside the workspace sandbox
  5. If the prompt includes a push-summary step, run that command with --file pointing to your temp file
  6. Verify the push succeeded by checking the JSON output for "success": true
  7. Clean up the temporary summary file

If summary generation fails:

  • Run ox agent <id> doctor — it can detect and help recover missing summaries
  • The session data is safe regardless; only the rich summary is missing

$ox agent session stop

Changes

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.

  1. 1mo ago First seen · 28 lines · 0 tokens per session scan C 5ec48b8a9f97

Subscribe to this mod's changes

ox-session-stop is a command published in the GitHub repository sageox/agentx (4 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 373 tokens. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.