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.
npx skills add cyanheads/met-museum-mcp-server --skill maintenancegit clone --depth 1 https://github.com/cyanheads/met-museum-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/cyanheads/met-museum-mcp-server/maintenance)<a href="https://agentmods.dev/skills/cyanheads/met-museum-mcp-server/maintenance"><img src="https://agentmods.dev/badge/skills/cyanheads/met-museum-mcp-server/maintenance/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/cyanheads/met-museum-mcp-server/maintenance"><img src="https://agentmods.dev/badge/skills/cyanheads/met-museum-mcp-server/maintenance.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 | $0.00075 | $0.04892 |
| Opus 5 | $0.00037 | $0.02446 |
| Sonnet 5 | $0.00015 | $0.00978 |
| Haiku 4.5 | $0.00007 | $0.00489 |
Grade A, and why
maintenance 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 today.
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.
This is a copy
100% identical to maintenance — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
- After running
bun update --latestyourself and wanting to review the impact (Mode B — typical) - To run the whole flow end-to-end — outdated check → update → investigate → adopt → verify (Mode A)
- Periodically, to check for skill drift from the package
Entry Modes
| Mode | Starting Point | First Step |
|---|---|---|
| A — Full flow | Lockfile is current; want to update | Step 1 |
| B — Post-update review | User already ran bun update --latest + bun run rebuild + bun run test |
Skip to Step 3 with the update output or a bun.lock diff |
Both modes converge at Step 3 and end at Step 8.
Steps
1. Survey what's outdated (Mode A only)
bun run devcheck --only outdated
Wraps bun outdated with the project's devcheck.config.json allowlist applied, so intentionally-pinned packages don't surface as actionable. Plain bun outdated works too if you want the unfiltered view.
Note: bun update --latest crosses semver majors; bun update alone respects ranges. Use --latest unless a package is intentionally pinned.
2. Apply the update (Mode A only)
bun update --latest
Capture the ↑ package old → new lines from stdout — these feed Step 3. Alternatively, diff bun.lock to surface version deltas after the fact.
3. Investigate changelogs
Invoke the changelog skill with the captured list of updated packages. It resolves each repo, fetches release notes (or CHANGELOG entries) between old and new versions, and cross-references changes against actual imports in src/. Output per package: what changed, impact on this project, action items.
Do not redo this investigation inline — the changelog skill handles tag-format detection, monorepo patterns, and fallbacks. If the skill cannot resolve a package (private repo, no tags, no CHANGELOG), note it in Step 8 under "Open decisions" and proceed.
4. Framework review (@cyanheads/mcp-ts-core)
Skill-version paradox. If node_modules/@cyanheads/mcp-ts-core/skills/maintenance/SKILL.md's version exceeds the one running, run Step 5 Phase A first and re-invoke maintenance — otherwise feature-adoption rows added in the new version silently don't surface. After Phase A, confirm the running skill version matches the package before continuing. If the session still has the old skill loaded, exit and restart.
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.
- today Changed · +1 lines 34656f9e0d16
- 10d ago First seen · 243 lines · 75 tokens per session scan A d86eacb0aa5a
maintenance is a skill published in the GitHub repository cyanheads/met-museum-mcp-server (4 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 4,892 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to maintenance, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
observations
List recent captured session observations (the Haiku-summarized voyage logs). Use when the user wants to see what Captain Memo has logged from past sessions.
wtf-happened
Retrieve a distilled timeline of the current troubleshooting incident and generate a runbook skeleton. Returns a concise summary by default, or the full untruncated timeline on request.
wtf-now
Add a manual observation to the WTF flight recorder journal. The entry is stored as a crafted (intentional) record. Classification of the entry's action type is handled by the background classifier — do not attempt to infer it here.
wtf
Launch the WTF flight recorder for a new troubleshooting incident. Archives any prior incident, prompts for an optional title, then puts Claude into flight recorder mode where significant observations, theories, and corrective actions are journaled automatically.
bun-runtime-http
Covers Bun.serve, HTTP server configuration, routing, streaming responses, WebSockets, TLS/SSL, and middleware with Bun's native APIs.
bun-snippets-cli
CLI snippets and command-line automation recipes with Bun.