release

A release-management guide for AgentGem, a software project with a core package and a desktop application.

In plain words
What is it for?
Use it when preparing a core or desktop release, including version bumps, changelog updates, pull requests, merges, and tags.
Why use it?
It explains how to update versions, write release notes, create release tags, and pass the required checks in the expected order.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/ninemindai/agentgem/release
Any agent
npx skills add ninemindai/agentgem --skill release
Clone the repo
git clone --depth 1 https://github.com/ninemindai/agentgem

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 804 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00046 $0.00804
Opus 5 $0.00023 $0.00402
Sonnet 5 $0.00009 $0.00161
Haiku 4.5 $0.00005 $0.00080

Measured 3d ago against content hash d1167fb210c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

.claude/skills/release/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cutting an AgentGem release

Core (@ninemind/agentgem) and the desktop app share one version number but are tagged separately: vX.Y.Z (core) and desktop-vX.Y.Z (desktop). A normal release ships both tags on the same commit.

1. Release worktree + branch

git fetch origin
git worktree add ../agentgem-worktrees/release-X.Y.Z -b release/X.Y.Z origin/main
cd ../agentgem-worktrees/release-X.Y.Z && pnpm install --frozen-lockfile

2. One release commit

Three files, one commit, message release: vX.Y.Z — core + desktop:

  • package.json + desktop/package.json — bump "version" in both.
  • CHANGELOG.md — Keep-a-Changelog style, two sections inserted above the previous release: ## [X.Y.Z] — \@ninemind/agentgem` (npm core) — YYYY-MM-DD(intro paragraph naming the release's themes + commit count fromgit log --oneline vPREV..origin/main | wc -l, then Added/Changed/Fixed) and ## [desktop-vX.Y.Z] — desktop app — YYYY-MM-DD` (desktop-specific changes, then a one-liner noting it embeds everything in core X.Y.Z).

3. PR → merge

Push, open a PR, wait for the test (24) gate, then rebase-merge (gh run watch <run-id> --exit-status, gh pr merge --rebase --delete-branch). --delete-branch errors on the local delete (main is checked out in another worktree) — the remote merge still succeeds; verify with git fetch + check origin/main.

4. Tag the main commit, then push tags

A rebase merge mints a new SHA — tagging the branch commit strands the tag off-main (this happened to v0.5.0/v0.6.0's branches; the tags were correctly placed on main).

git fetch origin
SHA=$(git log origin/main --format=%H --grep "release: vX.Y.Z" -1)
git tag -a vX.Y.Z         -m "vX.Y.Z — core + desktop"         "$SHA"
git tag -a desktop-vX.Y.Z -m "desktop-vX.Y.Z — core + desktop" "$SHA"
git push origin vX.Y.Z desktop-vX.Y.Z

5. What the tags trigger — and what stays manual

Step Trigger
Node 26 CI matrix automatic on v* / desktop-v* push (ci.yml)
Desktop build + GitHub release (latest*.yml for auto-update) automatic on desktop-v* (desktop-release.yml)
npm publish manual: npm publish from the tagged checkout — prepublishOnly runs clean + build + bundle-bins
Website desktop-download link manual follow-up PR pointing at desktop-vX.Y.Z

Read the full file on GitHub · 66 lines

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. 3d ago First seen · 66 lines · 46 tokens per session scan A d1167fb210c4

Subscribe to this mod's changes

release is a skill published in the GitHub repository ninemindai/agentgem (39 stars, last pushed 6d ago), licensed MIT. It adds 46 tokens to every session and 804 once invoked, about $0.0002 per session on Opus 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.