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 release-publishgit 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/release-publish)<a href="https://agentmods.dev/skills/confighub/confighub-skills/release-publish"><img src="https://agentmods.dev/badge/skills/confighub/confighub-skills/release-publish/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/release-publish"><img src="https://agentmods.dev/badge/skills/confighub/confighub-skills/release-publish.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 | $0.00067 | $0.03132 |
| Opus 5 | $0.00034 | $0.01566 |
| Sonnet 5 | $0.00013 | $0.00626 |
| Haiku 4.5 | $0.00007 | $0.00313 |
Grade A, and why
release-publish 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
release-publish
Execution mode: follow references/execution-modes.md. This Skill grants no automatic tool permission. After a fresh whole-Space scope preview, standalone use submits one requested publish or lifecycle mutation to the host permission system. Scope expansion, incomplete Target membership, failed gates, or missing destructive preconditions still require a stop; an external overlay may impose a stricter stop before Bash.
This skill preserves ordinary-language apply/deploy jobs while using the only current delivery contract: Component → Variant Space → immutable OCI Release → Argo CD/Flux pull → runtime. The retired cub-apply trigger families route here; they are retained explicitly in compatibility/no-loss-inventory.v1.json.
Current Release contract
cub release publish <space-slug>:
- reads
Space.ReleaseTargetIDand requires that Target to use ProviderTypeOCI; - bundles the EffectiveReleaseSet: every Unit in that Space whose
Unit.TargetID == Space.ReleaseTargetID; - captures each effective Unit at head unless
--revision <tag-slug>is supplied, in which case the server selects the highest Revision currently carrying that mutable TagID; - checks ValidationErrors; and
- creates one immutable Release with a ConfigHub
ReleaseID, bundleDigest, OCIManifestDigest,UnitCount, andPublished=true.
It has no Unit, Filter, ChangeSet, cross-Space selector, or dry-run flag. A ChangeSet groups/reviews/restores revisions but does not narrow publication. The current profile uses OCI Space Releases; older bridge/per-Unit delivery is historical context only and must not be offered as executable fallback.
Preserve the job without hiding a scope change
| Prior intent | Current disposition |
|---|---|
| apply one Unit / Unit list / Filter | compare the requested set with the whole EffectiveReleaseSet; ask the user to accept the newly disclosed scope or use a dedicated Variant Space |
| apply every pending Unit | identify pending heads, then disclose every effective Unit captured, including unchanged heads |
| apply a ChangeSet | verify its closed revisions, then preview the complete destination Space Release |
| dry-run apply | emit a read-only publication preview; never call it a server dry-run |
| apply a specific revision | use a complete revision Tag only after every effective Unit resolves to an exact tagged RevisionID/DataHash |
| cancel an in-flight Unit apply | historical per-Unit behavior; immutable Release publication has no equivalent cancellation job |
| direct ConfigHub/bridge delivery | unsupported by the reviewed current Release path, which accepts OCI only |
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 657538432f5f
- 12d ago First seen · 234 lines · 67 tokens per session scan A 10713edc95bf
release-publish is a skill published in the GitHub repository confighub/confighub-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 67 tokens to every session and 3,132 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.