Borrowing it
Nothing to install: this file belongs to sageox/ox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sageox/ox/main/.claude/commands/release.mdgit 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/release)<a href="https://agentmods.dev/commands/sageox/ox/release"><img src="https://agentmods.dev/badge/commands/sageox/ox/release/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/release"><img src="https://agentmods.dev/badge/commands/sageox/ox/release.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 | $0.02315 |
| Opus 5.5 | $0.00000 | $0.00926 |
| Sonnet 5.5 | $0.00000 | $0.00463 |
| Haiku 4.5 | $0.00000 | $0.00231 |
Grade A, and why
release 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 23d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prepare and create a new ox release.
Use when:
- Ready to release a new version of ox
- User says "release", "cut a release", "prepare release", "version bump"
Arguments: $ARGUMENTS (optional version number like "0.15.0", or empty to auto-propose)
Release Workflow
Follow these steps exactly:
Step 1: Pre-flight Checks
# Verify on main branch, clean working directory
git branch --show-current
git status
# Run the executable in-repo release gates
make lint
make test-release # full + coverage ratchets + slow + acceptance + digital twins
If tests or lint fail, fix issues before proceeding.
Step 1b: External Harness Compatibility Evidence
make test-integration
These tests launch real Claude Code instances and exercise hooks, signals, and
session pipelines end-to-end. Investigate failures, but do not represent this
as an automated release gate until ox-ilrr.4 provides machine-verifiable
current-binary provenance and attestation.
Step 1c: Smoke Tests (requires SAGEOX_CI_PASSWORD)
make smoke-test
This runs end-to-end tests against test.sageox.ai: auth, init, doctor, status, re-init, agent prime, session list, and clone-without-ox. If smoke tests fail, investigate before proceeding — these verify ox works in a real environment.
Step 1d: Run Walks (Human-Driven)
Coordinate in the Slack channel. A team member installs the release candidate and walks through core workflows on a real machine:
- Fresh setup —
ox login→ox initon a new repo →ox doctor→ox status - Agent prime — open Claude Code, verify
ox agent primeloads team context - Session recording — start a session, do some work, stop it, verify
ox session list - Team context — verify team knowledge appears via
ox agent team-ctx - Clone experience — clone the repo in a fresh directory, run
ox init - Doctor recovery — delete
.sageox/config.json, runox doctor, verify auto-repair - Upgrade path — if upgrading, verify
ox versionand existing config survive
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.
- 23d ago Changed · +3 lines 41efbe6e928b
- 24d ago Changed · +26 lines 21736a5b3e19
- 1mo ago Changed · +24 lines 81d662ad5ea9
- 1mo ago First seen · 197 lines · 0 tokens per session scan A 2491bf1f2403
release is a command published in the GitHub repository sageox/ox (64 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,315 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
wtfp:update
Check for a newer compatible package or plugin release and install it only after approval.
iterate
Iteration delivery — delivery check + archive + commit & tag + bump version.
run-loop
Chain-aware loop driver. Works through implementation-plan tasks unattended — branch, build, ship a draft PR, dispatch the verifier, checkpoint, repeat — until the target is reached, the circuit breaker trips, or the task budget is spent. Never merges.
rebase
Rebase OpenShift fork of an upstream repository to a new upstream release.
analyze-payload
Analyze a payload (rejected, accepted, or in-progress) with historical lookback to identify root causes of blocking job failures.
backport
Backport commits to multiple branches.