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/bioliminal/ml_randd_server/claude-mdgit clone --depth 1 https://github.com/Bioliminal/ML_RandD_ServerWrote 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/bioliminal/ml_randd_server/claude-md)<a href="https://agentmods.dev/instructions/bioliminal/ml_randd_server/claude-md"><img src="https://agentmods.dev/badge/instructions/bioliminal/ml_randd_server/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 | $0.01337 | $0.01337 |
| Opus 5 | $0.00668 | $0.00668 |
| Sonnet 5 | $0.00267 | $0.00267 |
| Haiku 4.5 | $0.00134 | $0.00134 |
Grade A, and why
ML_RandD_Server 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 4d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RnD_Server — ML & Analysis Server
Updated: 2026-04-21 Owner: AaronCarney
Project-wide context (team, pipeline architecture, constraints, GitLab label taxonomy) lives in the parent CLAUDE.md at projects/bioliminal/CLAUDE.md. This file covers repo-specific file organization and conventions.
Documentation conventions: see https://gitlab.com/bioliminal/bioliminal/-/blob/main/CONVENTIONS.md — header schema (Status / Created / Updated / Owner), git-author → gitlab-handle mapping, and the delete-over-archive rule for superseded content. Follow the header schema for every new doc under docs/.
Compliance & Privacy Posture
Not HIPAA. Binding regimes: WA MHMDA (opt-in, $7,500/violation, private right of action), FTC HBNR (~$53k/violation), GDPR Art 9 in EU (no wellness exception). IL BIPA HB 2984 pending would add neural data. sEMG is functionally biometric — 90–97% re-id from 0.8s of 4-channel data. Schema changes that touch sEMG, session consent, or retention must treat these as load-bearing constraints, not compliance theater.
Full analysis (always read, do not restate from memory): projects/bioliminal/research/synthesis/deep-read-semg-privacy-regulation-2026-04-15.md. Parent hub: projects/bioliminal/CLAUDE.md § "Compliance & Privacy Posture".
File Organization
Placement Rules
Files go where their primary purpose lives. This repo is public; internal strategy/ops/session content lives in the private bioliminal-ops repo, and literature content lives in the private research repo.
| If the file is primarily about... | It goes in... |
|---|---|
| A physical component, sensor, actuator, or form factor | hardware/ in this repo |
| Buying, sourcing, or pricing components | hardware/bom/ in this repo |
| Engineering decisions safe for public view: license audits, algorithm implementation notes, library comparisons | docs/research/ in this repo |
| Training scripts, model configs, dataset processing | ml/ in this repo |
| Application code, UI, API | software/ in this repo |
| Mobile/server contract handoffs (Dart interfaces, JSON schemas, fixtures) | operations/handover/mobile/ in bioliminal-ops |
| Build tooling, CI, Docker, scripts | tools/ in this repo |
| Literature: papers, synopses, synthesis docs, deep reads | research repo (private) |
| Strategy: commercial viability, GTM, investor-facing framing, L1/L2 plans, cross-domain decisions | bioliminal-ops repo (private) |
| Competitors, market sizing, pricing, regulatory strategy | market/ in bioliminal-ops |
| Cross-team internal comms, session handoffs, progress files | operations/comms/ or sessions/ in bioliminal-ops |
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.
- 4d ago First seen · 62 lines · 1,337 tokens per session scan A 62967ee924ba
ML_RandD_Server CLAUDE.md is an instructions file published in the GitHub repository Bioliminal/ML_RandD_Server (43 stars, last pushed 4mo ago), licensed MIT. It adds 1,337 tokens to every session, about $0.0067 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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.