Borrowing it
Nothing to install: this file belongs to PackmindHub/packmind. 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/PackmindHub/packmind/main/.agents/skills/release-proprietary/SKILL.mdgit clone --depth 1 https://github.com/PackmindHub/packmindWrote 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/packmindhub/packmind/release-proprietary)<a href="https://agentmods.dev/skills/packmindhub/packmind/release-proprietary"><img src="https://agentmods.dev/badge/skills/packmindhub/packmind/release-proprietary/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/packmindhub/packmind/release-proprietary"><img src="https://agentmods.dev/badge/skills/packmindhub/packmind/release-proprietary.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 | $0.00085 | $0.02752 |
| Opus 5.5 | $0.00034 | $0.01101 |
| Sonnet 5.5 | $0.00017 | $0.00550 |
| Haiku 4.5 | $0.00009 | $0.00275 |
Grade A, and why
release-proprietary 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a full Packmind proprietary release with version {{version}}.
This skill orchestrates a cross-repository release that spans the OSS sibling (../packmind, cloned next to the proprietary repo) and the proprietary repo itself (the current working directory). All real release content (version bumps, CHANGELOG) lives on OSS; the proprietary side receives the OSS commit through the oss-sync workflow and gets its own release/{{version}} tag pointing at a different SHA than the OSS tag — see below.
Invocation requirement: run this skill from the root of the proprietary repo, with the OSS sibling checked out at ../packmind. All commands below assume that layout.
Dual-SHA model — important:
- On OSS, the
release/{{version}}tag points at the release commit itself (subjectchore: release {{version}}). That commit's tree contains OSS code, which is what OSS deployments need. - On proprietary, the same tag points at the sync-merge commit that brought the OSS release into proprietary
main. The OSS release commit has no proprietary-only files in its tree, so tagging it on proprietary would break deployments (the build can't find@packmind/proprietary/*modules). The sync-merge commit's tree combines OSS-at-release with the proprietary-only files, which is what proprietary deployments need.
The wait/tag scripts handle this for you — Phase 2 emits the proprietary merge SHA, and Phase 3 tags that SHA.
Repository layout assumed by every command in this file:
- OSS repo:
../packmind(remotePackmindHub/packmind) - Proprietary repo:
.— the current working directory (remotePackmindHub/packmind-proprietary)
Scripts live next to this file under ./scripts/. From the proprietary repo root, paths are .claude/skills/release-proprietary/scripts/<name>.
Phase 0 — Pre-flight (proprietary repo)
0.1 Feature flags audit gate (MANDATORY)
Before doing anything, stop and ask the user:
Has the
feature-flags-auditskill been run on the proprietary repo for this release? (yes / no)
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/bump-versions.mjs 991 B runs code
- scripts/changelog-next.mjs 1.8 KB runs code
- scripts/changelog-release.mjs 2.7 KB runs code
- scripts/check-ci.sh 2.6 KB runs code
- scripts/check-oss-sync-pr.sh 1.3 KB runs code
- scripts/commit-next-cycle.sh 613 B runs code
- scripts/commit-release.sh 1003 B runs code
- scripts/tag-release.sh 3.6 KB runs code
- scripts/wait-for-oss-sync.sh 3.7 KB runs code
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 · 207 lines · 85 tokens per session scan A 60a4add4d372
release-proprietary is a skill published in the GitHub repository PackmindHub/packmind (319 stars, last pushed 4d ago), licensed Apache-2.0. It adds 85 tokens to every session and 2,752 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 2026-09-22.
Other skills, from other repositories
gsd-complete-milestone
Archive completed milestone and prepare for next version.
skill-ship
Package and finalize completed work for delivery — use when a feature is done and ready to ship.
release
Release a new version of the DevoxxGenie IntelliJ plugin — prompt for the target version, bump it in the build files, write a curated CHANGELOG.md entry and plugin.xml change-notes from the git/PR history since the last tag, build to verify, then commit, tag, and publish a matching GitHub release. Use this whenever…
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.
release-engineering
Plan and verify software releases with versioning, changelogs, release branches, feature flags, canaries, migration gates, rollback, deployment checks, and release readiness. Use when preparing a release, shipping a risky PR, coordinating app/backend/database rollout, recovering from a bad deploy, or defining release…
release-debrief
Summarises the delta between a tool's latest release and the last summary the user saw. Use when the user asks about what's new, the latest release, release notes, or the changelog of one of the supported tools: Claude Code, OpenCode, llama-swap, or llama.cpp.