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/jvogan/motif/agents-mdgit clone --depth 1 https://github.com/jvogan/motifWrote 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/jvogan/motif/agents-md)<a href="https://agentmods.dev/instructions/jvogan/motif/agents-md"><img src="https://agentmods.dev/badge/instructions/jvogan/motif/agents-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 | $0.00943 | $0.00943 |
| Opus 5 | $0.00472 | $0.00472 |
| Sonnet 5 | $0.00189 | $0.00189 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
motif AGENTS.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 3d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Motif for Claude Science — Agent Guide
This is a portable artifact/plugin repository with a narrow Motif-owned MCP App connector. Keep it independent of any desktop application, native database, or predecessor identity.
Start here
npm run typecheck
npm test
npm run preview:motif
Use npm run typecheck, never npx tsc --noEmit. The root tsconfig.json is
solution-style ("files": [] plus project references), so --noEmit finds no
files and exits 0 unconditionally, while tsc -b follows the project
references. It is not a weaker check; it does not check this repository.
scripts/__tests__/gate-parity.test.mjs fails if the typecheck script drifts
to --noEmit.
For visible changes, open preview/motif-artifact.html in a real browser and
exercise wide, narrow, light, dark, resized-panel, mouse, and keyboard states.
A passing DOM assertion is not proof that a control is legible or reachable.
Important paths
motif.html— Vite entrysrc/artifacts/motif-artifact.tsx— standalone runtime entrysrc/artifacts/motif-artifact.css— artifact stylingsrc/artifacts/motif-for-claude-science-plugin/— Claude plugin sourcesrc/artifacts/motif-for-claude-science-skill/— standalone skillmcp/motif/— bounded Motif MCP tools and resource registrationsrc/mcp-app/— full-workbench MCP App bridgescripts/build-claude-science-artifact.mjs— deterministic distributablescripts/build-preview.mjs— isolated browser previewe2e/— focused real-browser workflow coverage
Product contracts
- Product name: Motif for Claude Science
- Package/plugin slug:
motif-for-claude-science - Current release version is
0.3.6and must stay aligned in runtime, package, manifest, and changelog. - New schemas, environment variables, page APIs, output files, and provenance
identifiers use
motif/MOTIF_names. - Do not reintroduce predecessor names or initials in public contracts. Do not claim that an older connector is Motif.
window.motifHelp()is the runtime manifest for page-local APIs.
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.
- 3d ago First seen · 90 lines · 943 tokens per session scan A 234c8d02fb1c
motif AGENTS.md is an instructions file published in the GitHub repository jvogan/motif (47 stars, last pushed 4d ago), licensed MIT. It adds 943 tokens to every session, about $0.0047 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
OmicsClaw AGENTS.md
AGENTS.md instructions for TianGzlab/OmicsClaw, covering agents.md — omicsclaw guide for ai coding agents, repository working contract, project overview, setup and pip install -e .
wisp-science AGENTS.md
AGENTS.md instructions for xuzhougeng/wisp-science, covering agents.md, project orientation, repository layout, engineering rules and verification commands.
bio-gene-to-reference-tree copilot-instructions.md
Copilot instructions for Hongda-Zhao/bio-gene-to-reference-tree, a project described as: Auditable agent skill for resolving protein queries, selecting references, and planning reproducible phylogenetic trees.
protein-mcp-server CLAUDE.md
Instructions for cyanheads/protein-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
proto-tools GEMINI.md
Instructions for evo-design/proto-tools, a project described as: A universal infrastructure layer for generative biology.
uniprot-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/uniprot-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.