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.
curl -O https://raw.githubusercontent.com/wandb/wandb-mcp-server/main/.agents/skills/develop-wandb-mcp-tools/SKILL.mdgit clone --depth 1 https://github.com/wandb/wandb-mcp-serverWrote 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.
[](https://agentmods.dev/skills/wandb/wandb-mcp-server/develop-wandb-mcp-tools)<a href="https://agentmods.dev/skills/wandb/wandb-mcp-server/develop-wandb-mcp-tools"><img src="https://agentmods.dev/badge/skills/wandb/wandb-mcp-server/develop-wandb-mcp-tools/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.
<a href="https://agentmods.dev/skills/wandb/wandb-mcp-server/develop-wandb-mcp-tools"><img src="https://agentmods.dev/badge/skills/wandb/wandb-mcp-server/develop-wandb-mcp-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00078 | $0.00925 |
| Opus 5.5 | $0.00031 | $0.00370 |
| Sonnet 5.5 | $0.00016 | $0.00185 |
| Haiku 4.5 | $0.00008 | $0.00093 |
Grade A, and why
develop-wandb-mcp-tools 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Develop W&B MCP Tools
Establish the contract
- Read
CONTRIBUTING.mdand the relevant tool, registration, and tests before editing. - Prefer extending an existing tool. Add a new public tool only when the request explicitly requires a distinct capability.
- Record the intended public contract before coding:
- input schema and validation;
- read, write, or read/write behavior;
- idempotency and ambiguous-timeout behavior;
- canonical tool group, tool profile, access mode, prerequisite, and risk metadata;
- bounded request, iteration, and response behavior;
- stable error codes and retry guidance.
- Keep caller-supplied GraphQL out of normal tools. Use documented SDK APIs or fixed, application-owned query-only projections.
Implement through shared boundaries
- Put tool behavior in
src/wandb_mcp_server/mcp_tools/and register it throughregister_tools(). - Add every public tool exactly once to
src/wandb_mcp_server/runtime-contract.json; generate release evidence and documentation from that packaged contract rather than copying manifests. - Treat
WANDB_MCP_TOOL_PROFILEas the deployment capability envelope andWANDB_MCP_ACCESS_MODE=read-onlyas a monotonic subtraction. Neither replaces call-time authorization. - Reuse the shared API configuration, URL resolution, error sanitizer, response budget, deadline, and
InstrumentedFastMCPboundary. - Classify the tool in
admission.py; an unclassified tool is deliberately treated as heavy. - Preserve public links on
WANDB_BASE_URL; never expose a server-side route. - Never log raw arguments, prompts, queries, filters, credentials, resource identifiers, or upstream response bodies.
- Add only bounded, low-cardinality telemetry dimensions.
- Do not retry non-idempotent writes. Return an explicit unknown outcome when a timeout makes write completion ambiguous.
- For optional external services, require an explicit reviewed profile and typed endpoint configuration, validate the endpoint, bound input and polling, disable redirects when credentials could cross origins, and keep the group out of managed profiles until its entitlement boundary is approved.
- For credential-forwarding HTTP tools, stream through a finite byte cap before JSON decoding, reject unexpected redirects or encodings, and bound the request by the active MCP tool deadline.
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.
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 · +1 lines 209f238accc1
- 1mo ago First seen · 60 lines · 78 tokens per session scan A 2bc3d5c576c1
develop-wandb-mcp-tools is a skill published in the GitHub repository wandb/wandb-mcp-server (72 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 925 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.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…