release-and-publish

release-and-publish is a skill for Claude Code from cyanheads/attack-surface-mcp-server. It costs 112 tokens per session (2,864 once invoked), scanned A, a copy of release-and-publish, Apache-2.0.

A release process for publishing an MCP project to the registries and package stores it targets. It handles destinations such as npm, the MCP Registry, GitHub Releases, and GHCR, a container image registry.

In plain words
What is it for?
Use it after version bumps, changelog updates, a release commit, and an annotated tag are already complete and the working tree is clean.
Why use it?
It reduces missed release steps by verifying the prepared release, pushing its commit and tag, and publishing each applicable package or bundle.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the attack-surface-mcp-server plugin — 32 skills, 1 MCP server shipped together

Good fit Use it after version bumps, changelog updates, a release commit, and an annotated tag are already complete and the working tree is clean.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cyanheads/attack-surface-mcp-server/release-and-publish
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 cyanheads/attack-surface-mcp-server --skill release-and-publish
Clone the repo
git clone --depth 1 https://github.com/cyanheads/attack-surface-mcp-server

Made for: Claude Code.

Or install attack-surface-mcp-server, the plugin that ships this one along with the rest of its 32 skills, 1 MCP server.

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-and-publish

README.md
[![agentmods](https://agentmods.dev/badge/skills/cyanheads/attack-surface-mcp-server/release-and-publish/github.svg)](https://agentmods.dev/skills/cyanheads/attack-surface-mcp-server/release-and-publish)
Your own site
<a href="https://agentmods.dev/skills/cyanheads/attack-surface-mcp-server/release-and-publish"><img src="https://agentmods.dev/badge/skills/cyanheads/attack-surface-mcp-server/release-and-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.

agentmods 80×15 button for release-and-publish

Your own site · 80×15
<a href="https://agentmods.dev/skills/cyanheads/attack-surface-mcp-server/release-and-publish"><img src="https://agentmods.dev/badge/skills/cyanheads/attack-surface-mcp-server/release-and-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,864 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 92% copy Near-identical to another mod 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 $0.00112 $0.02864
Opus 5 $0.00056 $0.01432
Sonnet 5 $0.00022 $0.00573
Haiku 4.5 $0.00011 $0.00286

Measured 9d ago against content hash 957109bba580, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

release-and-publish 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 9d 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.

- **MCP Registry**: `curl -s "https://registry.modelcontextprotocol.io/v0.1/servers/<mcpName>/versions/<version>"` — must return HTTP 200 with `server.version` matching `<version>` (`mcpName` is the `name` field from `se
Origin

This is a copy

92% identical to release-and-publish — 20 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/release-and-publish/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Preconditions

This skill runs after git wrapup. By the time it's invoked:

  • Pre-wrapup verification is done (field-test, security-pass, polish-docs-meta as applicable)
  • package.json version is bumped
  • changelog/<major.minor>.x/<version>.md is authored
  • CHANGELOG.md is regenerated
  • README and every version-bearing file is in sync
  • Release commit (chore: release v<version>) exists
  • Annotated tag (v<version>) exists locally
  • Working tree is clean

If any are missing, halt and tell the user to finish wrapup first. Do not attempt to redo wrapup work from inside this skill.

Failure Protocol

Steps 3–7 are network-bound. For those, retry transient failures up to 2 times with short backoff (~5 s before the first retry, ~15 s before the second) before halting. All other steps halt on the first non-zero exit — they're deterministic and a second attempt won't change the outcome.

Retry on transient patterns

Match stderr (case-insensitive) against any of these — if matched, the failure is almost always a network blip; retry:

  • integrity check failed / IntegrityCheckFailed — corrupt tarball during download
  • ECONNRESET / EAI_AGAIN / ETIMEDOUT / ENOTFOUND — network layer
  • connection reset / connection refused — transport blip
  • timed out / request timeout — server or network timeout
  • HTTP 502 / 503 / 504 — transient registry error

Before retrying docker buildx --push (step 7), run docker builder prune -f to drop any cached corrupt layer. Skip this extra step for other retries.

Never retry on idempotent-success signals

These mean the step already succeeded on a prior run — treat as success and proceed to the next step:

  • npm (bun publish): version already exists, You cannot publish over the previously published versions
  • MCP Registry (mcp-publisher publish): cannot publish duplicate version
  • GitHub Release (gh release create): release already exists — fall back to gh release upload --clobber (see step 6)

Read the full file on GitHub · 222 lines

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. 9d ago First seen · 222 lines · 112 tokens per session scan A 957109bba580

Subscribe to this mod's changes

release-and-publish is a skill published in the GitHub repository cyanheads/attack-surface-mcp-server (1 stars, last pushed 10d ago), licensed Apache-2.0. It adds 112 tokens to every session and 2,864 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 92% identical to release-and-publish, differing in 20 lines, and is treated as a copy.

Related

Other skills, from other repositories

commit-pr

Mandatory Codex/Copilot publication adapter for opencode-swarm. Use for every GitHub issue assignment that results in code changes, commits, pushes, draft PRs, PR body edits, PR readying, release notes, or CI closeout. Must be loaded before git push, gh pr create, gh pr edit, or gh pr ready. Routes to the single…

ZaxbyHub/opencode-swarm · 100 tokens

contributing

Codex adapter for the opencode-swarm contribution checklist. Use when preparing user-visible changes, release note fragments, local validation, branch hygiene, PR checklist items, or contribution-policy compliance before publishing work.

ZaxbyHub/opencode-swarm · 44 tokens

release-aur

Use when creating, updating, reviewing, or publishing Arch User Repository (AUR) packages. Runs /release-aur plan first, reviews PKGBUILD/.SRCINFO/build/namcap evidence, and only recommends /release-aur publish after a GO decision.

Firstp1ck/pi-coding-agent-forge · 57 tokens

deploy-safely

Build, test, push, deploy, and verify with rollback through Git on failure.

veryfront/veryfront-code · 22 tokens

fable-release

Audit and certify repository merge and release readiness against required quality gates, clean git working trees, and verified distribution artifacts. Use when preparing a release tag, validating release checklist criteria, publishing npm/PyPI packages, or certifying a branch for merge — even if the user does not…

imMamdouhaboammar/get-fable · 113 tokens

release

Cut a release of the msteams channel plugin — validate, bump the version in all four manifests, write a CHANGELOG entry, commit, push, tag, and publish a GitHub release. Use whenever the user says "release", "cut a release", "version bump", "ship it", "publish", "tag a release", "changelog and push", or finishes a…

gtapps/msteams-channel · 89 tokens