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/crossread/scholion/skillnpx skills add CrossRead/scholion --skill skillgit clone --depth 1 https://github.com/CrossRead/scholionWhat 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 | $0.00205 | $0.02846 |
| Opus 5 | $0.00102 | $0.01423 |
| Sonnet 5 | $0.00041 | $0.00569 |
| Haiku 4.5 | $0.00020 | $0.00285 |
Grade A, and why
scholion 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.
This is a copy
100% identical to scholion — 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scholion — the short instruction
Scholion brings one person's own medical data — a full genome, laboratory forms, prescriptions, wearable exports — into a single profile and shows the links between them. It is exploratory and educational, and it is not a medical device: it does not diagnose, and it neither starts nor stops therapy.
You work through the command line: you ask the person to run a command and you read its output. You get no access to their machine, and their profile never leaves it.
First: make it run
scholion --version # already installed?
pip install scholion # if not — an ordinary package, no account, no key
Show the product on a fictional person before asking for anything real:
scholion init --demo # a fictional person — not anybody's real data
scholion overview # flags, gaps, counters
scholion limits # what CANNOT be said from this data, and what would close it
Use init --demo, not demo — demo writes to a directory of its own, and
the next overview will report an empty profile. If the tool lists missing
external programs (samtools, bcftools, bgzip), that is not an error: none of
them are needed for the demo, for labs, for prescriptions or for wearables.
Then: ask for what is missing, once
scholion limits returns items, and the ones with "kind": "profile" are the
facts this product cannot derive and will not invent — sex, year of birth,
height, reference population, which wearable answers. Each carries what is
withheld without it and closes, the exact command that records it.
Ask from that list, not from this page. The list is computed from the profile, so it holds only what is actually absent, and it shrinks as they answer. A list written into an instruction goes stale the day a sixth precondition is added, and then a model asks for five things for ever.
Ask in ONE message rather than one question at a time, and add the two that are measurements rather than fixed facts:
What ships with it
2 files 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.
- 2d ago First seen · 222 lines · 205 tokens per session scan A db14fedb27c9
scholion is a skill published in the GitHub repository CrossRead/scholion (3 stars, last pushed 5d ago), licensed Apache-2.0. It adds 205 tokens to every session and 2,846 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to scholion, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
Git Workflow
Agent-safe git operations with SSH commit signing. Handles commit, push, and signing configuration to avoid interactive prompt hangs.
add-tool
Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.
api-linter
MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.
api-context
Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.enrich, ctx.content), and when to use each.
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…