codeatlas-mcp-server: Skill for Claude Code

.claude/skills/publish-mcp-server/SKILL.md

publish-mcp-server is a skill for Claude Code from giauphan/codeatlas-mcp-server. It costs 36 tokens per session (505 once invoked), scanned C, original, MIT.

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.

In plain words
What is it for?
Building the package, previewing and inspecting its archive, checking npm access, handling two-factor authentication, publishing, and verifying the release.
Why use it?
It helps catch incorrect versions, missing documentation, authentication problems, and accidental inclusion of secrets or unrelated files before publishing.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions Claude Code.

This is giauphan/codeatlas-mcp-server's own configuration. It tells Claude Code how to work on codeatlas-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything codeatlas-mcp-server configures →

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.

agentmods badge for publish-mcp-server

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.

agentmods 80×15 button for publish-mcp-server

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 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 505 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.00505
Opus 5 $0.00018 $0.00253
Sonnet 5 $0.00007 $0.00101
Haiku 4.5 $0.00004 $0.00051

Measured 9d ago against content hash 582039993028, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

publish-mcp-server scanned grade C with 2 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 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 600 ~/.npmrc

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Restart Claude Code before checking `~/.claude/hooks/brain-*.sh`, hook commands in `~/.claude/settings.json`, and `~/.claude/brain-save.log`. Confirm commands use `$HOME`-based paths, not a machine-specific `/home/<user>
.claude/skills/publish-mcp-server/SKILL.md · 53 lines

What it actually says

Publish CodeAtlas MCP Server

Before publishing

  1. Update package.json to a new unused semver version. Check with npm view codeatlas-mcp-server versions --json.
  2. Ensure the root README.md documents npm installation, environment variables, and codeatlas-mcp install-hooks.
  3. Build and inspect the exact package:
    npm run build
    npm pack --dry-run
    npm pack
    tar -tzf codeatlas-mcp-server-<version>.tgz
    
  4. Confirm only intended files are included. Never package .env, credentials, tokens, service-account files, or unrelated local data. Remove the temporary tarball.

Authentication

Keep the npm token only in the user-level config, never in the repository:

printf '%s\n' '//registry.npmjs.org/:_authToken=TOKEN' > ~/.npmrc
chmod 600 ~/.npmrc
npm whoami

The account must own or have write permission for codeatlas-mcp-server. If publish returns E403 mentioning 2FA, use npm publish --otp=123456, or create a granular token with package Read and write permission and explicitly enabled 2FA bypass. A 404 on PUT usually means the authenticated account/token lacks package write permission; do not change the version to work around it.

Publish and verify

npm publish
npm view codeatlas-mcp-server version
npm view codeatlas-mcp-server readme

Do not publish on the user's behalf without explicit authorization.

Verify Second Brain hooks

codeatlas-mcp install-hooks --dry-run
codeatlas-mcp install-hooks

Restart Claude Code before checking ~/.claude/hooks/brain-*.sh, hook commands in ~/.claude/settings.json, and ~/.claude/brain-save.log. Confirm commands use $HOME-based paths, not a machine-specific /home/<user> path.

Rollback by restoring the timestamped settings.json.bak-install-* backup, removing installed brain hook scripts, and restarting Claude Code. Never run the real installer while untrusted hook output is polluting the current session; restart first.

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 · 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 today), licensed MIT. It adds 36 tokens to every session and 505 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

stage-10-pr

You are a delivery agent. Push. Create PR. Write audit trail. Close finding. Your output is a merge-ready pull request with a complete audit trail linking every change back to the original finding, through the PRD, to the verification report. The PR description is machine-generated from stage artifacts — not…

cdeust/ai-architect-mcp · 4 tokens

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…

microsoft/agent-framework · 103 tokens

changelog-scan

Scan merged PRs and commits since a given reference, extract titles, labels, types, and signals. Produces structured input for release notes drafting.

cobusgreyling/loop-engineering · 35 tokens

draft-release-notes

Turn changelog-scan output into polished, categorized release notes draft. Propose only.

cobusgreyling/loop-engineering · 23 tokens

git-integration

Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.

a5c-ai/babysitter · 39 tokens

release-notes

Create release notes for a new version tag. Gathers all commits, PRs, issues fixed, and breaking changes since a previous release. Creates the release notes markdown file, tags the repo, and pushes. Asks the user to confirm the base version to diff against.

agentic-community/mcp-gateway-registry · 59 tokens