Borrowing it
Nothing to install: this file belongs to berntpopp/clingen-link. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/berntpopp/clingen-link/main/AGENTS.mdgit clone --depth 1 https://github.com/berntpopp/clingen-linkWrote 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/berntpopp/clingen-link/agents-md)<a href="https://agentmods.dev/instructions/berntpopp/clingen-link/agents-md"><img src="https://agentmods.dev/badge/instructions/berntpopp/clingen-link/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/berntpopp/clingen-link/agents-md"><img src="https://agentmods.dev/badge/instructions/berntpopp/clingen-link/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02942 | $0.02942 |
| Opus 5.5 | $0.01177 | $0.01177 |
| Sonnet 5.5 | $0.00588 | $0.00588 |
| Haiku 4.5 | $0.00294 | $0.00294 |
Grade A, and why
clingen-link 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 6d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Shared repository instructions for agentic coding tools working in clingen-link.
Project
clingen-link is a Python MCP server that grounds gene/disease/variant questions
in ClinGen curated evidence across four domains:
gene-disease validity, gene dosage, clinical actionability, and variant
pathogenicity (ERepo). It is built on the gnomad-link house style: a
hand-authored FastMCP v3 facade with the full canonical response envelope and
Streamable-HTTP transport (unified / http). Data is served from a self-contained,
read-only SQLite snapshot (bundled in the package), with a thin live HTTP layer
for single-record drill-down.
Primary areas (under clingen_link/):
etl/— offline snapshot builder (fetch → parse → freshness → build). Never in the request path. Entry:clingen-link refresh(orpython -m clingen_link.etl refresh).store/— read-only SQLite query layer (gene resolution/alias, per-domain queries). Opens the bundled snapshot read-only.api/— live HTTP layer (httpx.AsyncClient) for ERepo / actionability SEPIO drill-down: semaphore concurrency + jittered retry + queue-wait →rate_limited- typed fault taxonomy.
services/— business logic merging store + live;async-lrucaching lives here; builds per-recordrecommended_citation.models/— Pydantic response models per domain.mcp/— the MCP surface:facade.py(create_clingen_mcp),errors.py(canonical envelope +run_mcp_tool),next_commands.py,resources.py,shaping.py, andtools/*.py(13 tools grouped by domain).
Entry point: a single typer app at clingen_link/cli.py (clingen-link console
script → clingen_link.cli:app) with serve / config / health / refresh /
version commands. Logging is structlog (clingen_link/logging_config.py,
JSON in prod / console in --dev, with asgi-correlation-id). Other areas:
tests/—unit/(default fast path) andintegration/(live drift tests,@pytest.mark.integration, excluded from the default path).docker/— Dockerfile + Compose overlays + README. The bundled snapshot.zstis shipped in the image.docs/—architecture.md,usage.md, and design specs/plans underdocs/superpowers/.
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.
- 6d ago Changed 6dfca20d9fcb
- 1mo ago Changed · +68 lines · +1,278 tokens per session fdf8c29fe0bb
- 1mo ago First seen · 139 lines · 1,664 tokens per session scan A 197db40aff1c
clingen-link AGENTS.md is an instructions file published in the GitHub repository berntpopp/clingen-link (0 stars, last pushed 3d ago), licensed MIT. It adds 2,942 tokens to every session, about $0.0118 per session on Opus 5.5. 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 2026-08-31.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.