What is publish-mcp-server?

A release checklist for publishing the CodeAtlas MCP server as an npm package. npm is the package registry commonly used to distribute JavaScript and Node.js software.

Building the package, previewing and inspecting its archive, checking npm access, handling two-factor authentication, publishing, and verifying the release.

It helps catch incorrect versions, missing documentation, authentication problems, and accidental inclusion of secrets or unrelated files before publishing.

How giauphan/codeatlas-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to giauphan/codeatlas-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/giauphan/codeatlas-mcp-server/main/.claude/skills/publish-mcp-server/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/giauphan/codeatlas-mcp-server

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/giauphan/codeatlas-mcp-server/publish-mcp-server/github.svg)](https://agentmods.dev/skills/giauphan/codeatlas-mcp-server/publish-mcp-server)

Your own site

<a href="https://agentmods.dev/skills/giauphan/codeatlas-mcp-server/publish-mcp-server"><img src="https://agentmods.dev/badge/skills/giauphan/codeatlas-mcp-server/publish-mcp-server/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/giauphan/codeatlas-mcp-server/publish-mcp-server"><img src="https://agentmods.dev/badge/skills/giauphan/codeatlas-mcp-server/publish-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 659 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.

Model	Per session	Once invoked
Fable 5.1	$0.00029	$0.00659
Opus 5.5	$0.00012	$0.00264
Sonnet 5.5	$0.00006	$0.00132
Haiku 4.5	$0.00003	$0.00066

Measured 18d ago against content hash 8c230c672c39, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

publish-mcp-server 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 18d 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.

.claude/skills/publish-mcp-server/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeAtlas MCP Server npm Releases

Release process

The supported release process is automated by .github/workflows/publish.yml. A push to main or manual dispatch runs its CI job, then semantic-release analyzes Conventional Commits on main and publishes only if a release is warranted. feat selects a minor release; fix and perf select patch; breaking changes select major. Docs-only commits normally do not create a release.

Do not direct contributors to bump package.json with npm version or run a separate npm publish command. Manual workflow dispatch runs the same release automation and commit analysis. The workflow determines the version and tag. The package manifest version, Git release tags, and live npm version may differ at a given checkout; verify published metadata with npm when discussing the current release.

Before describing changes to the release process, inspect:

.github/workflows/publish.yml
.github/workflows/ci.yml
.github/workflows/npm-rollback.yml
.releaserc.json
package.json

For job dependencies, npm validation retries, and rollback behavior, use the pipeline runbook.

npm authentication and validation

The GitHub release workflow uses its protected npm environment and secrets. Never print or commit npm tokens. Troubleshoot authentication by checking workflow environment/secrets access and package permissions. Do not work around authentication by choosing a different version.

After semantic-release creates a version output, the workflow fetches that version from npm with npm pack --prefer-online, retrying 10 times at 15-second intervals. It checks required files in the tarball, absence of test files, the latest dist-tag, and global CLI installation. The validation job is skipped when semantic-release produced no version output.

Manual rollback

.github/workflows/npm-rollback.yml is manually dispatched with a known-good version and optional bad version to deprecate. It verifies the target exists, moves the npm latest tag, and may deprecate the bad version. It does not revert commits, remove Git tags, or delete a published version.

Read the full file on GitHub · 68 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.

18d ago Changed · +15 lines · -7 tokens per session scan C → A 8c230c672c39
2mo ago First seen · 53 lines · 36 tokens per session scan C 582039993028

Subscribe to this mod's changes

publish-mcp-server is a skill published in the GitHub repository giauphan/codeatlas-mcp-server (10 stars, last pushed 6d ago), licensed MIT. It adds 29 tokens to every session and 659 once invoked, about $0.0001 per session on Opus 5.5. 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.

Git and workflow Releases agentic-ai ai ast claude code-analysis codebase-intelligence

publish-mcp-server next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
publish-mcp-servergiauphan/codeatlas-mcp-server	Skill	10	6d ago	MIT	A	29	Claude Code
stage-10-prcdeust/ai-architect-mcp	Skill	1	6mo ago	MIT	A	4	Claude Code
release-announcementpaperclipai/paperclip	Skill	111k	yesterday	MIT	A	42	Claude Code, Codex
agent-release-managerruvnet/ruflo	Skill	81k	yesterday	MIT	A	16	Claude Code
agent-release-swarmruvnet/ruflo	Skill	81k	yesterday	MIT	A	19	Claude Code
agent-github-modesruvnet/ruflo	Skill	81k	yesterday	MIT	A	21	Claude Code
github-automationruvnet/ruflo	Skill	81k	yesterday	MIT	A	61	Claude Code

codeatlas-mcp-server: Skill for Claude Code