release

A release guide for BrowserMesh, a browser-control project distributed through npm and the MCP Registry. It covers versioning, publishing, protected tags, and the remaining setup required for automated releases.

In plain words
What is it for?
Preparing releases, reviewing Release Please changes, diagnosing failed npm or registry publication, and checking why a version was not published.
Why use it?
It explains why a release may stop before reaching npm or the MCP Registry, including missing npm trusted publishing configuration.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/scrolldynasty/browsermesh/release
Any agent
npx skills add scrollDynasty/BrowserMesh --skill release
Clone the repo
git clone --depth 1 https://github.com/scrollDynasty/BrowserMesh

Made for: Claude Code, Codex.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 963 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00058 $0.00963
Opus 5 $0.00029 $0.00481
Sonnet 5 $0.00012 $0.00193
Haiku 4.5 $0.00006 $0.00096

Measured 2d ago against content hash 39098314425a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

release 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.scrollDynasty/browsermesh"
.claude/skills/release/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Releasing BrowserMesh

TODO — release is currently blocked on a maintainer action

npm Trusted Publishing is not configured for the browsermesh package. This is not a code problem and no change in this repository fixes it.

  • 0.2.0 could not publish over OIDC and was pushed by hand.
  • publish.yml will fail the same way on the next version until a trusted publisher naming this repository, publish.yml, and the npm environment is added on npmjs.com.
  • Because registry publication runs after npm publish in the same job, it has not run either. The MCP Registry's latest entry is still 0.1.5 pointing at the old multi-agent-browser-mcp name.

Configuring the trusted publisher first lets the next release correct the registry on its own. Do not work around this by publishing manually again without saying so — see docs/IMPLEMENTATION_STATUS.md.

Also outstanding and maintainer-only: GitHub repository topics are unset.

The chain

Conventional Commit PR title
  → reviewed PR with green required checks
  → merge to master
  → release-please updates a Release PR
  → maintainer merges the Release PR
  → release-please creates the vX.Y.Z tag and GitHub Release
  → publish workflow verifies source and installed tarball
  → npm Trusted Publishing (OIDC)
  → MCP Registry publication (GitHub OIDC)

No ordinary push or feature PR publishes anything. Merging the Release PR is the only maintainer gesture that starts a release.

What bumps a version

release-please-config.json uses release-type: node with bump-minor-pre-major and bump-patch-for-minor-pre-major. Pre-1.0, feat and fix both produce a patch. chore, docs, ci, test, build, and refactor produce no release — use them for tooling changes that should not cut a version.

PR titles are validated against feat fix docs refactor perf test build ci chore revert, and the subject must start lowercase.

Version consistency

Four places carry the version and must agree: package.json, both version fields in server.json, and the generated src/infrastructure/generated/version.ts. Release Please updates all of them via extra-files. npm run check:version fails on drift and runs as pretypecheck, so a stale generated module turns typecheck red before anything is type-checked.

Read the full file on GitHub · 104 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. 2d ago First seen · 104 lines · 58 tokens per session scan A 39098314425a

Subscribe to this mod's changes

release is a skill published in the GitHub repository scrollDynasty/BrowserMesh (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 58 tokens to every session and 963 once invoked, about $0.0003 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

browser_harness

../../SKILL.md.

browser-use/browser-harness · 0 tokens

browser-harness

Always use browser-harness for any web interaction: automation, scraping, testing, or site/app work.

browser-use/browser-harness · 25 tokens

deep-reverse

Use only for explicit web or API protocol reverse engineering: endpoint discovery, request replay, signature/token/encryption analysis, JavaScript runtime tracing, browser-independent reproduction, or crawler implementation that must not depend on browser automation. Do not use for one-off visible-page extraction or…

KuiChi-x/reverseloom · 61 tokens

web-crawl

Get data from websites with the least necessary complexity. Use for quick lookups, visible-page extraction, search results, tables, pagination, detail-page traversal, downloadable files (Excel/CSV/PDF/ZIP), embedded page state, internal JSON/XHR APIs, bulk collection, reusable crawler generation, and delivery in any…

KuiChi-x/reverseloom · 108 tokens

eric-task-master

Install, connect, and use Eric Task Master for durable Playwright browser jobs with persistent or ephemeral Profiles, live fast-auto-human behavior control, task queues, progress health, semantic diagnostics, recovery, artifacts, and composable Task Packs.

npcworkspace-cmyk/eric-task-master · 52 tokens

opencli-usage

Use at the start of any OpenCLI session — this is the top-level map of what opencli can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".

jackwener/OpenCLI · 74 tokens