release

release is a skill for Claude Code, Codex from heptameta/heptabase-cli-skills. It costs 110 tokens per session (1,488 once invoked), scanned A, original, MIT.

A release workflow for publishing new versions of the heptabase-cli-skills plugin package across supported coding-tool marketplaces and registries.

In plain words
What is it for?
Use it when checking release readiness, increasing the package version, creating a matching Git tag, or publishing a GitHub release.
Why use it?
It coordinates version changes, tags, compatibility information, release notes, and package manifests so installed users can receive updates.

Skill for Claude CodeCodex

Written for Claude Code and Codex: allowed-tools in frontmatter, but also agents/openai.yaml present. Also seen: reads .claude/ paths; mentions Claude Code; mentions OpenCode.

Part of the heptabase-cli-skills plugin — 4 skills shipped together

Good fit Use it when checking release readiness, increasing the package version, creating a…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/heptameta/heptabase-cli-skills/release
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.

Any agent
npx skills add heptameta/heptabase-cli-skills --skill release
Clone the repo
git clone --depth 1 https://github.com/heptameta/heptabase-cli-skills

Made for: Claude Code, Codex.

Or install heptabase-cli-skills, the plugin that ships this one along with the rest of its 4 skills.

Wrote 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.

agentmods badge for release

README.md
[![agentmods](https://agentmods.dev/badge/skills/heptameta/heptabase-cli-skills/release.svg)](https://agentmods.dev/skills/heptameta/heptabase-cli-skills/release)
Your own site
<a href="https://agentmods.dev/skills/heptameta/heptabase-cli-skills/release"><img src="https://agentmods.dev/badge/skills/heptameta/heptabase-cli-skills/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,488 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00110 $0.01488
Opus 5 $0.00055 $0.00744
Sonnet 5 $0.00022 $0.00298
Haiku 4.5 $0.00011 $0.00149

Measured 7d ago against content hash 7bbf6a5cd06b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 7d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/bump-version.mjs, scripts/preflight.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Releasing heptabase-cli-skills

This repo ships a public plugin package installed via the Claude Code marketplace, Cursor, npx skills, and OpenCode. Claude Code caches installed plugins by resolved plugin version, so users only receive updates when the version changes — pushing commits without a bump ships nothing.

Conventions (and why)

  • .claude-plugin/plugin.json version is the single source of truth. Claude Code resolves the version as: plugin.jsonmarketplace.json plugin entry → commit SHA. Never add a version to a marketplace.json plugin entry — it would silently shadow future strategy changes.
  • .cursor-plugin/plugin.json must mirror the same version on every release (Cursor reads its version from that file).
  • Tag format: vX.Y.Z matching the manifest version.
  • GitHub release title: Compatible with CLI v<range>, where <range> is metadata.heptabase-cli-version-range from skills/heptabase-cli/SKILL.md (e.g. 0.4.x → "Compatible with CLI v0.4.x"). The title states compatibility, not features, and stays identical across releases in the same CLI range.
  • Release notes are auto-generated from merged PR titles (--generate-notes). There is no CHANGELOG file. This means changes should land via PRs with clear conventional-commit titles (feat: ..., fix: ...) — the PR title is the changelog entry.

Version bump rules

Bump When
patch Documentation-only skill fixes; no CLI compatibility change
minor New CLI commands supported, new non-breaking CLI behavior, or a new CLI compatibility range
major Rare package-level changes only: plugin rename, removing the primary skill, changing the distribution model

Read the full file on GitHub · 75 lines

Files

What ships with it

3 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.

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. 7d ago First seen · 75 lines · 110 tokens per session scan A 7bbf6a5cd06b

Subscribe to this mod's changes

release is a skill published in the GitHub repository heptameta/heptabase-cli-skills (149 stars, last pushed 9d ago), licensed MIT. It adds 110 tokens to every session and 1,488 once invoked, about $0.0006 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.