What is release-wandb-mcp-server?

A release checklist for publishing a W&B MCP Server, including source checks, package checks, documentation checks, and test gates. W&B, or Weights & Biases, is a platform for tracking machine-learning experiments and tools.

It is for preparing release branches, checking versions and artifacts, reviewing readiness, documenting evidence, and preparing rollback.

It reduces the risk of publishing an incomplete, unverifiable, or incorrectly packaged release.

How wandb/wandb-mcp-server configures Codex

Reuse

Borrowing it

Nothing to install: this file belongs to wandb/wandb-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/wandb/wandb-mcp-server/main/.agents/skills/release-wandb-mcp-server/SKILL.md

Clone the repo

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

Made for: Codex.

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/wandb/wandb-mcp-server/release-wandb-mcp-server/github.svg)](https://agentmods.dev/skills/wandb/wandb-mcp-server/release-wandb-mcp-server)

Your own site

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

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 871 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	$0.00065	$0.00871
Opus 5.5	$0.00026	$0.00348
Sonnet 5.5	$0.00013	$0.00174
Haiku 4.5	$0.00006	$0.00087

Measured 28d ago against content hash 848aaf69a78d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release-wandb-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 28d 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.

.agents/skills/release-wandb-mcp-server/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release W&B MCP Server

Follow the controller

Read RELEASING.md and the target note under docs/releases/ completely.
Record exact source and tree SHAs. Treat moving branches and mutable tags as navigation only, never evidence.
Run the candidate gate:
```
uv run --no-sync python scripts/public_release.py \
  preflight --version "$VERSION" --gate candidate
```
Verify generated configuration/profile documentation with python scripts/public_release.py docs --check.
Verify the packaged src/wandb_mcp_server/runtime-contract.json hash, then inspect the exact profile/access-mode pairs generated by python scripts/public_release.py profiles --all. Do not substitute counts, subsets, or copied tool lists.
Run the locked/latest SDK, Python, security, isolated-wheel, and installed MCP protocol gates specified by RELEASING.md.
Stop at a draft candidate unless the user explicitly authorizes the next action and repository protection allows it.

Fail closed

Do not continue when the controller reports a dirty tree, inconsistent version, stale SHA, unsigned or misplaced tag, missing release note, incomplete exact profile evidence, mutable artifact, missing scan/SBOM, or mismatched digest. Record a skipped or unavailable check as a blocker, never a pass.

After the approved release PR merges, source-gate must bind the merge SHA to the reviewed head tree, required current-head checks, approval, and resolved conversations before anyone creates the signed tag.

If that post-merge gate or a final security check finds a source defect, stop before tagging or deployment. Fix it in a new reviewed PR, treat all earlier candidate evidence as stale, and stage the repaired tree again. Never amend the already-reviewed history or reuse evidence from the superseded tree.

Build only through scripts/public_release.py build into a new directory outside the checkout. Never reuse dist/. The attest command produces a deterministic predicate for the protected signer; it is not signed evidence by itself.

Read the full file on GitHub · 92 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

agents/openai.yaml 227 B

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.

28d ago Changed · +19 lines 848aaf69a78d
1mo ago First seen · 73 lines · 65 tokens per session scan A cb99b14b14b6

Subscribe to this mod's changes

release-wandb-mcp-server is a skill published in the GitHub repository wandb/wandb-mcp-server (72 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 871 once invoked, about $0.0003 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 2026-09-18.

DevOps and cloud Git and workflow Releases

release-announcement

Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.

paperclipai/paperclip · 42 tokens

release

Fully automate a release with version-bump and childhood.

thedotmack/claude-mem · 13 tokens

release-notes

Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.

phuryn/pm-skills · 57 tokens

wandb-mcp-server: Skill for Codex