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 agentmods add skills/anthropics/knowledge-work-plugins/startnpx skills add anthropics/knowledge-work-plugins --skill startgit clone --depth 1 https://github.com/anthropics/knowledge-work-pluginsWhat 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 | $0.00049 | $0.00763 |
| Opus 5 | $0.00024 | $0.00381 |
| Sonnet 5 | $0.00010 | $0.00153 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
start 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 2d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bio-Research Start
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
You are helping a biological researcher get oriented with the bio-research plugin. Walk through the following steps in order.
Step 1: Welcome
Display this welcome message:
Bio-Research Plugin
Your AI-powered research assistant for the life sciences. This plugin brings
together literature search, data analysis pipelines,
and scientific strategy — all in one place.
Step 2: Check Available MCP Servers
Test which MCP servers are connected by listing available tools. Group the results:
Literature & Data Sources:
- ~~literature database — biomedical literature search
- ~~literature database — preprint access (biology and medicine)
- ~~journal access — academic publications
- ~~data repository — collaborative research data (Sage Bionetworks)
Drug Discovery & Clinical:
- ~~chemical database — bioactive compound database
- ~~drug target database — drug target discovery platform
- ClinicalTrials.gov — clinical trial registry
- ~~clinical data platform — clinical trial site ranking and platform help
Visualization & AI:
- ~~scientific illustration — create scientific figures and diagrams
- ~~AI research platform — AI for biology (histopathology, drug discovery)
Report which servers are connected and which are not yet set up.
Step 3: Survey Available Skills
List the analysis skills available in this plugin:
| Skill | What It Does |
|---|---|
| Single-Cell RNA QC | Quality control for scRNA-seq data with MAD-based filtering |
| scvi-tools | Deep learning for single-cell omics (scVI, scANVI, totalVI, PeakVI, etc.) |
| Nextflow Pipelines | Run nf-core pipelines (RNA-seq, WGS/WES, ATAC-seq) |
| Instrument Data Converter | Convert lab instrument output to Allotrope ASM format |
| Scientific Problem Selection | Systematic framework for choosing research problems |
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.
- 2d ago First seen · 80 lines · 49 tokens per session scan A 6016fe5c2895
start is a skill published in the GitHub repository anthropics/knowledge-work-plugins (23,791 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 763 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…