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.
npx skills add confighub/confighub-skills --skill promote-releasegit clone --depth 1 https://github.com/confighub/confighub-skillsWrote 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/confighub/confighub-skills/promote-release)<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.
<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>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 | $0.00068 | $0.06705 |
| Opus 5 | $0.00034 | $0.03352 |
| Sonnet 5 | $0.00014 | $0.01341 |
| Haiku 4.5 | $0.00007 | $0.00671 |
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.
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 withcub 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
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.
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.
- 2d ago Changed b0ffe1b0c0bb
- 12d ago First seen · 367 lines · 68 tokens per session scan A 7787225df15d
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.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.