Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/atretyak1985/swarmerynpx agentmods add skills/atretyak1985/swarmery/release-promotionWrote 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/atretyak1985/swarmery/release-promotion)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/release-promotion"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/release-promotion/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/atretyak1985/swarmery/release-promotion"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/release-promotion.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 | $0.00063 | $0.04084 |
| Opus 5.5 | $0.00025 | $0.01634 |
| Sonnet 5.5 | $0.00013 | $0.00817 |
| Haiku 4.5 | $0.00006 | $0.00408 |
Grade A, and why
release-promotion scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf http://${SERVICE_URL}/health || echo "Health check failed" How it starts
The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Promote the project's service images and chart versions across environments using immutable digests, producing updated entries in the version-pinning repo (if the project uses one -- project.json → repos; referenced below as <versions-repo>) with current/previous tracking for auditability and fast rollback. This skill manages the cross-environment promotion lifecycle; it defers the single-environment Helm upgrade execution to deployment and pull-based GitOps reconciliation to gitops-promotion.
When to use this skill
- Trigger A -- Promoting an image from dev to staging or staging to production
- Trigger B -- Rolling back a promotion to the previous known-good digest
- Trigger C -- Updating
<versions-repo>after a verified deployment - Trigger D -- Reviewing promotion history in Git for audit purposes
- Trigger E -- Coordinating Helm chart version promotion alongside image digest promotion
When NOT to use this skill
- Anti-trigger A -- Code-level refactoring rollback (git revert) -> use
refactor-planinstead - Anti-trigger B -- Feature-flag toggles that change behavior without deploying a new image
- Anti-trigger C -- Schema-only migrations that deploy without a new service image -> use
migration-checkinstead - Anti-trigger D -- Hotfix cherry-picks that bypass the normal promotion queue -- handle as expedited single-repo deployments with post-hoc
<versions-repo>update - Anti-trigger E -- Single-environment Helm upgrade orchestration -> use
deploymentinstead - Anti-trigger F -- Cluster-level infrastructure operations -> use
kubernetes-deploymentinstead
Required environment
- Runtime mount:
.claude/skills/release-promotion/SKILL.md - Tools / libraries:
helm(v3+),kubectl,gcloudCLI (for digest lookup via the registry) - Repositories: the version-pinning repo (version state) and the chart repo (project.json → repos)
- Reversibility profile: hard-to-reverse -- promotion writes to
<versions-repo>(Git-tracked, revertible) and triggers a Helm upgrade on the target cluster; rollback requires a new promotion commit pointing toprevious_digest
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.
- 1mo ago First seen · 328 lines · 63 tokens per session scan A 06bdb3a8ecee
release-promotion is a skill published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed today), licensed Apache-2.0. It adds 63 tokens to every session and 4,084 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
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.
release-publish
Publish an approved Orchard release.
release-review
Review Orchard deployment manifests.
orchard-release
Check deployment evidence and recovery conditions.
orchard-review
Review a release proposal.