AutoSci is an AI research platform organized around a wiki, with an agent that supports stages of scientific work such as reading, experimentation, writing, and retaining knowledge across projects. It is for people building or using AI-assisted research workflows, with Claude Code, Codex, and OpenCode adaptations available. The catalogue add-ons extend those agent-specific workflows.
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 instructions/skyllwt/autosci/claude-mdgit clone --depth 1 https://github.com/skyllwt/AutoSciWrote 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/instructions/skyllwt/autosci/claude-md)<a href="https://agentmods.dev/instructions/skyllwt/autosci/claude-md"><img src="https://agentmods.dev/badge/instructions/skyllwt/autosci/claude-md.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 | $0.00584 | $0.00584 |
| Opus 5 | $0.00292 | $0.00292 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
AutoSci CLAUDE.md 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 5d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ΩmegaWiki — Runtime Contract
Edit i18n/en/CLAUDE.md, not the active copy at root. Run ./setup.sh --lang en to sync.
Repository Layout
wiki/— product surface.index.mdis the catalog;log.mdis append-only; subdirs per entity kind;wiki/graph/is auto-generated.runtime/— contract source (schema + policy + templates). Readruntime/CLAUDE.mdbefore changing any rule.raw/— user-owned{papers,notes,web}/(read-only) + skill-writablediscovered/,tmp/.tools/— Python helpers (research_wiki.pyis the wiki engine;lint.pyis the validator).
Full tree: docs/runtime-directory-structure.en.md.
Link Syntax
Wikilinks: [[slug]]. Slugs are lowercase, hyphen-separated, no spaces.
Hard Rules
raw/{papers,notes,web}are user-owned, read-only. Skills append only toraw/discovered/orraw/tmp/.wiki/graph/is derived. Modify only viatools/research_wiki.py(add-edge,add-citation,rebuild-*).wiki/log.mdis append-only. Never rewrite in place.- Forward link → write reverse simultaneously. Rules in
runtime/schema/xref.yaml. - User-facing skill flags (those listed in a skill's
argument-hint) are user-owned. Do not invent, flip, or drop them based on repo state. If the user omitted one, use a default only when the skill documents omission behavior; otherwise ask.
Where to look
| Need | Source |
|---|---|
| Page frontmatter fields, enums, defaults, lifecycle | runtime/schema/entities.yaml |
| Page body section structure | runtime/templates/{kind}.md.tmpl |
| Edge types, attributes, direction, confidence | runtime/schema/edges.yaml |
| Forward → reverse link rules | runtime/schema/xref.yaml |
| Slug rule, ownership, edge storage location | runtime/schema/conventions.yaml |
| Field/edge write permissions per skill | runtime/policy/writers.yaml |
| Changing the contract / regen | runtime/CLAUDE.md |
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.
- 5d ago First seen · 41 lines · 584 tokens per session scan A 9f7f1c4ded7b
AutoSci CLAUDE.md is an instructions file published in the GitHub repository skyllwt/AutoSci (1,659 stars, last pushed 6d ago), licensed MIT. It adds 584 tokens to every session, about $0.0029 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-release stance: foundation over blast radius, repository layout, commands and host sandbox failures.