release-engineering-board

release-engineering-board is a skill for Claude Code, Codex from GhostlyGawd/engineering-board. It costs 73 tokens per session (735 once invoked), scanned A, original, MIT.

A release checklist and procedure for the Engineering Board source repository. It coordinates version updates, tests, package rebuilding, changelog changes, tagging, publishing, and release checks.

In plain words
What is it for?
Use it when preparing or publishing a maintainer release, updating the product version, rebuilding or pinning the MCP bundle, or checking GitHub, PyPI, and MCP Registry releases.
Why use it?
It removes the risk of updating one release file while missing another or publishing an unverified package. It keeps the release steps in a defined order.

Skill for Claude CodeCodex

Part of the engineering-board plugin — 6 skills, 21 commands, 8 agents, 4 hooks, 1 MCP server, 1 plugin shipped together

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/ghostlygawd/engineering-board/release-engineering-board
Any agent
npx skills add GhostlyGawd/engineering-board --skill release-engineering-board
Clone the repo
git clone --depth 1 https://github.com/GhostlyGawd/engineering-board

Made for: Claude Code, Codex.

Or install engineering-board, the plugin that ships this one along with the rest of its 6 skills, 21 commands, 8 agents, 4 hooks, 1 MCP server, 1 plugin.

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-engineering-board

README.md
[![agentmods](https://agentmods.dev/badge/skills/ghostlygawd/engineering-board/release-engineering-board.svg)](https://agentmods.dev/skills/ghostlygawd/engineering-board/release-engineering-board)
Your own site
<a href="https://agentmods.dev/skills/ghostlygawd/engineering-board/release-engineering-board"><img src="https://agentmods.dev/badge/skills/ghostlygawd/engineering-board/release-engineering-board.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 735 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00073 $0.00735
Opus 5 $0.00036 $0.00367
Sonnet 5 $0.00015 $0.00147
Haiku 4.5 $0.00007 $0.00073

Measured 4d ago against content hash ed022cde59d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

release-engineering-board 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 4d 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.

maintainers/skills/release-engineering-board/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Engineering Board

Use this skill only in the GhostlyGawd/engineering-board source repository. Do not use it in a repository that only installs the Engineering Board plugin.

Use the repository script for release preparation. Do not update release files independently.

Prepare the release

  1. Read docs/RELEASING.md.

  2. Confirm that the release branch is clean.

  3. Confirm that the Codex manifest, Claude manifest, marketplace, Python package, MCP manifests, README badge, architecture release line, product release boundary, and security support line have the current version.

  4. Select the next Semantic Versioning value from the [Unreleased] changes.

  5. Preview the coordinated change:

    python3 scripts/prepare-release.py <version>
    
  6. Review every listed file, including the current-truth documentation, and the prospective MCP bundle checksum.

  7. Apply the same plan:

    python3 scripts/prepare-release.py <version> --apply
    
  8. Run the complete test suite:

    bash tests/run-all.sh
    
  9. From a host with Claude Code installed, validate the prepared Claude marketplace with warnings treated as errors:

    claude plugin validate --strict .
    

    Stop if the validator is unavailable, reports a warning, or exits nonzero. Keep this host-native release gate separate from the dependency-free CI toolchain.

  10. Commit and push the release-preparation change.

If approved review changes modify the prepared bundle, use --refresh with the current prepared version. Preview the refresh before you apply it. Refresh must not create another changelog section. Do not use refresh to change the target version.

Publish the release

Publish only from a commit on main. Do not move an existing tag.

Use .github/workflows/release.yml with:

  • the exact v<version> tag;
  • the exact main commit;
  • MCP Registry publication when the release must update that registry;
  • PyPI publication when the release must update that package.

Read the full file on GitHub · 100 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. 4d ago First seen · 100 lines · 73 tokens per session scan A ed022cde59d1

Subscribe to this mod's changes

release-engineering-board is a skill published in the GitHub repository GhostlyGawd/engineering-board (0 stars, last pushed 5d ago), licensed MIT. It adds 73 tokens to every session and 735 once invoked, about $0.0004 per session on Opus 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.