Borrowing it
Nothing to install: this file belongs to panaversity/ksor. 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/panaversity/ksor/main/.agents/skills/release/SKILL.mdgit clone --depth 1 https://github.com/panaversity/ksorWrote 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/panaversity/ksor/release)<a href="https://agentmods.dev/skills/panaversity/ksor/release"><img src="https://agentmods.dev/badge/skills/panaversity/ksor/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/panaversity/ksor/release"><img src="https://agentmods.dev/badge/skills/panaversity/ksor/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 | $0.00110 | $0.01266 |
| Opus 5.5 | $0.00044 | $0.00506 |
| Sonnet 5.5 | $0.00022 | $0.00253 |
| Haiku 4.5 | $0.00011 | $0.00127 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Releasing
The airlock — main is always releasable, never auto-released
feature PR ──CI gate + review──▶ main nothing publishes; a changeset
│ (intent file) is recorded
▼
"Version Packages" PR the staging area — accumulates
│ every pending changeset; can sit
│ open for a month while work lands
a human merges it the ONLY action that releases
▼
release job re-runs the gate red = no publish
FULL gate, then publishes
with provenance (OIDC)
Release timing is controlled entirely by when the Version Packages PR is merged. Review it as a release-notes reader: the changelog it generates is what adopters will read.
Testing before publish
Three layers, all before anything reaches the registry:
- The PR gate — including the tarball test, which asserts the shipped bytes (dist entries, docs, LICENSE, NOTICE, CHANGELOG in the pack).
- A live walk of the real artifact (mandatory for CLI changes, per
$implement-spec):
pnpm packinpackages/ksor, install the tarball into a fresh temp dir, run the actual binary — help exit 0, unknown verb exit 1 with slug, designed verb exit 2, bundled docs present. - The Version PR review — the human sign-off. Since the org toggle was
enabled (2026-08-21) this PR is opened by
github-actions[bot], and its CI waits for approval: the run sits inaction_requiredwith zero jobs, sogh pr checksanswers "no checks reported on the 'changeset-release/main' branch". That reads like a repo with no CI and is not — approve it and the full eight-job gate runs (it passed on #48). Approve from the PR's Checks tab or withgh api -X POST repos/panaversity/ksor/actions/runs/<id>/approve, and do it before merging: after the merge the release job re-runs the whole gate anyway, but then a failure costs you a red release instead of a red PR.
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 · 91 lines · 110 tokens per session scan A c16cb2349cb7
release is a skill published in the GitHub repository panaversity/ksor (232 stars, last pushed 23d ago), licensed Apache-2.0. It adds 110 tokens to every session and 1,266 once invoked, about $0.0004 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
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
release-publish
Publish an approved Orchard release.
release-review
Review Orchard deployment manifests.
orchard-release
Check deployment evidence and recovery conditions.
release-notes
Draft short release notes from a list of changes. Use when the user asks for changelogs, release notes, or a concise product update.
release
Cut and maintain Observal release branches, prepare alpha, beta, RC, stable, and patch releases, backport merged main PRs, inspect release status, verify published artifacts, and recover failed release operations. Use for Observal maintainer release tasks and release-process changes, not for installing or upgrading an…