Borrowing it
Nothing to install: this file belongs to Pipelex/pipelex-mcp. 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/Pipelex/pipelex-mcp/main/.claude/skills/bump-sdks/SKILL.mdgit clone --depth 1 https://github.com/Pipelex/pipelex-mcpWrote 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/pipelex/pipelex-mcp/bump-sdks)<a href="https://agentmods.dev/skills/pipelex/pipelex-mcp/bump-sdks"><img src="https://agentmods.dev/badge/skills/pipelex/pipelex-mcp/bump-sdks.svg" alt="Measured on agentmods" 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 | $0.00217 | $0.04790 |
| Opus 5 | $0.00109 | $0.02395 |
| Sonnet 5 | $0.00043 | $0.00958 |
| Haiku 4.5 | $0.00022 | $0.00479 |
Grade A, and why
bump-sdks 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 6d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bump the @pipelex SDKs
This repo depends on two published @pipelex packages, and both are pre-1.0:
| Package | What it gives this repo | Source repo |
|---|---|---|
@pipelex/sdk |
PipelexApiClient — every API call the capabilities make |
Pipelex/pipelex-sdk-js |
@pipelex/mthds-ui |
GraphViewer / GraphSpec — the run-graph and run-follow views |
Pipelex/mthds-ui |
Because they are 0.x, npm treats the leading zero as the major: a ^0.9.0 range auto-resolves patches only, so every minor bump (0.9.0 → 0.10.0) needs a deliberate edit. Bump both by default. Only narrow to one package, or to a specific version, if the user asked for that.
Work through the steps below, showing the user each file change and each install before moving on. The judgment in this skill is concentrated in Step 4 — reading the changelogs and deciding what this repo actually has to migrate — so spend your effort explaining there, not narrating the mechanical steps.
Why this repo needs more than make all
Every capability here talks to the SDK through a hand-written narrow interface (CatalogClient, RunClient, MethodFetchClient, …) that restates the SDK method signatures this repo uses. Tests inject fakes that satisfy those local interfaces. That design is good for testing and it creates one specific blind spot you must plan around:
- A type change in the SDK is caught — each capability falls back to
new PipelexApiClient(...)where the local interface is expected, sotscstructurally compares the two and fails. - A behavior or wire-shape change is not caught. The local interface still compiles, the fakes still return the shape they were written for, and
make allgoes green while the real client is broken against the live API.
This is not hypothetical. On SDK 0.9.0 the whole suite passed while mthds_list_methods failed on every real call with wire.map is not a function — the platform had reshaped GET /v1/methods into a page object and 0.9.0 still called .map() on the response. Step 4 and Step 7 exist to catch exactly that class of failure, and Step 7 is now two real targets (make test-e2e and make smoke) rather than a probe you assemble by hand.
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.
- 6d ago First seen · 224 lines · 217 tokens per session scan A 6aeae14fded4
bump-sdks is a skill published in the GitHub repository Pipelex/pipelex-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 217 tokens to every session and 4,790 once invoked, about $0.0011 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…