promote-release

promote-release is a skill for Claude Code from confighub/confighub-skills. It costs 68 tokens per session (6,705 once invoked), scanned A, original, MIT.

A release-promotion workflow for moving configuration changes from one ConfigHub environment to another. A variant is a separately managed copy of an environment, and a ChangeSet groups selected changes for review.

In plain words
What is it for?
Use it to promote changes to staging or production, update only selected Units, inspect withheld merges, or investigate why an override was replaced.
Why use it?
It helps move the intended scope forward while showing what was not merged, which Units are behind, and where overrides or conflicts need attention.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the confighub-skills plugin — 16 skills, 1 command, 1 hook shipped together

Good fit Use it to promote changes to staging or production, update only selected Units, inspect withheld merges, or investigate why an override was replaced.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/confighub/confighub-skills/promote-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 confighub/confighub-skills --skill promote-release
Clone the repo
git clone --depth 1 https://github.com/confighub/confighub-skills

Made for: Claude Code.

Or install confighub-skills, the plugin that ships this one along with the rest of its 16 skills, 1 command, 1 hook.

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 promote-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/confighub/confighub-skills/promote-release/github.svg)](https://agentmods.dev/skills/confighub/confighub-skills/promote-release)
Your own site
<a href="https://agentmods.dev/skills/confighub/confighub-skills/promote-release"><img src="https://agentmods.dev/badge/skills/confighub/confighub-skills/promote-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.

agentmods 80×15 button for promote-release

Your own site · 80×15
<a href="https://agentmods.dev/skills/confighub/confighub-skills/promote-release"><img src="https://agentmods.dev/badge/skills/confighub/confighub-skills/promote-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,705 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 $0.00068 $0.06705
Opus 5 $0.00034 $0.03352
Sonnet 5 $0.00014 $0.01341
Haiku 4.5 $0.00007 $0.00671

Measured 2d ago against content hash b0ffe1b0c0bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

promote-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 2d 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.

skills/promote-release/SKILL.md · 367 lines

How it starts

The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.

promote-release

Execution mode: follow references/execution-modes.md. This Skill grants no automatic tool permission. After fresh preflight and an exact source/destination/scope preview, standalone use submits one requested promotion to the host permission system; publication is a later, separate host-permission call. An external overlay may stop either step before Bash.

Promote a release forward. There are two mechanisms; pick by scope:

  • Variant spaces (space-level, preferred for the common case). cub variant promote <space> reconciles a whole variant Space with the upstream Space it was cloned from — in one command. Set up with cub variant create (clone a Space into a variant) and, for a brand-new base, cub variant upload (ingest rendered manifests into a base Space).
  • ChangeSet-wrapped bulk upgrade (fine-grained / cross-space). Manual cub unit update --patch --upgrade --where … inside a ChangeSet, when you need a partial scope, a cross-Space fleet push, or explicit ChangeSet grouping, review, and set-wise restore.

Before acting, confirm cub auth status succeeds (it calls the server's /me to verify the token; if it fails, ask the user to run cub auth login). Confirm verbs and flags with cub <verb> --help before composing — never invent flags. This skill hands off the cluster rollout to release-publish.

When to use

  • "Promote to staging / prod", "roll forward", "push the release", "upgrade the downstreams to match upstream".
  • The decision question: "is this ready?", "which Units are behind their upstream?".
  • "The promotion overwrote a value this environment had set" / "this environment didn't pick up the change" — the protection and conflicts sections.
  • Standing up a new environment/region/tenant variant of an existing Space.
  • Pushing a shared base out to every downstream across env-Spaces.

Do not load for

Read the full file on GitHub · 367 lines

Files

What ships with it

1 file 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. 2d ago Changed b0ffe1b0c0bb
  2. 12d ago First seen · 367 lines · 68 tokens per session scan A 7787225df15d

Subscribe to this mod's changes

promote-release is a skill published in the GitHub repository confighub/confighub-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 68 tokens to every session and 6,705 once invoked, about $0.0003 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 2026-08-31.