Borrowing it
Nothing to install: this file belongs to littlebearapps/untether. 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/littlebearapps/untether/master/.codex/skills/untether-release/SKILL.mdgit clone --depth 1 https://github.com/littlebearapps/untetherWrote 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/littlebearapps/untether/untether-release)<a href="https://agentmods.dev/skills/littlebearapps/untether/untether-release"><img src="https://agentmods.dev/badge/skills/littlebearapps/untether/untether-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/skills/littlebearapps/untether/untether-release"><img src="https://agentmods.dev/badge/skills/littlebearapps/untether/untether-release.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 | $0.00063 | $0.00684 |
| Opus 5.5 | $0.00025 | $0.00274 |
| Sonnet 5.5 | $0.00013 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
untether-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 18d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Untether Release
Overview
Untether ships from one repo: feature branches → PR → dev (CI publishes rc
versions to TestPyPI) → PR dev→master (Nathan merges → auto-tag-on-master.yml
creates vX.Y.Z → release.yml publishes to PyPI). release.yml checks that
the tag matches pyproject.toml; src/untether/__init__.py reads __version__
from the installed package metadata, so there is nothing to bump there.
Agents MUST NOT push to master, merge PRs that target master, create
v* tags, or run gh release. Full rules: CLAUDE.md → "Release guard" and
.claude/rules/release-discipline.md.
Workflow
1) Choose version + date
- rc:
X.Y.ZrcNondev(commitchore: staging X.Y.ZrcN). rc versions get no CHANGELOG section of their own and are never tagged. - stable:
X.Y.Zwith a release date (YYYY-MM-DD).
2) Update changelog (stable)
Add a top section to CHANGELOG.md: ## vX.Y.Z (YYYY-MM-DD), with subsections
from fixes, changes, breaking, docs, tests. Every entry links its
issue: [#N](https://github.com/littlebearapps/untether/issues/N). Put
user-facing changes first.
3) Bump versions
pyproject.toml:project.version = "<version>"uv.lock: runuv lockso the root package version matches.
4) Update spec + docs
docs/reference/specification.mdheader:# Untether Specification vX.Y.Z [YYYY-MM-DD]([unreleased]while the version is still in rc).README.md/docs/faq/faq.mdif the release changes a user-facing surface (see.claude/rules/help-faq.md).
5) Run checks
just check(ruff format check, ruff, ty, pytest)uv lock --checkpython3 scripts/validate_release.py
6) Integration tests + attestation
Run the tiers required by docs/reference/integration-testing.md against
@untether_dev_bot, then scripts/run-integration-tests.sh <version> --manual
to write the attestation marker that scripts/fleet-rollout.sh requires.
7) Hand off
Open the PR to dev (rc) or the dev→master PR (stable) and stop. Tagging,
PyPI publishing and the GitHub Release happen automatically after Nathan merges.
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.
- 18d ago Changed · -5 lines · +16 tokens per session 127b42faee25
- 1mo ago First seen · 68 lines · 47 tokens per session scan A ab6e5a1586a5
untether-release is a skill published in the GitHub repository littlebearapps/untether (74 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 684 once invoked, about $0.0003 per session on Opus 5.5. 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
release
Generic release assistant — analyzes repo release rules, caches them in .omc/RELEASERULE.md, then guides the release.
publish
Publish oh-my-opencode to npm by triggering the GitHub Actions publish workflow and verifying its artifacts. Ship-only: never runs pre-publish-review or re-reviews merged code unless the user explicitly asks. Argument: . Triggers: publish, release, deploy, npm publish.
pre-publish-review
Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…
get-unpublished-changes
Compare HEAD with the latest published npm versions and list all unpublished changes by release layer. Triggers: unpublished changes, changelog, what changed, whats new.
cmux-release
Prefer the /release command. It determines the new version (minor by default), gathers the Changelog line from each PR merged since the last stable tag, updates CHANGELOG.md, runs ./scripts/bump-version.sh, commits, runs ./scripts/release-pretag-guard.sh, then tags and pushes.
gh-cli
Patterns for invoking the GitHub CLI (gh v2.100.0+) from agents. Use when the task mentions GitHub, gh, pull requests/PRs, issues, releases, gists, Actions/workflow runs, forks, repo cloning, reviews, or you need exact gh commands. Covers pagination, repo targeting, search vs list, discussions, projects, rulesets…