Borrowing it
Nothing to install: this file belongs to colbyw5/phenoforge. 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/colbyw5/phenoforge/main/AGENTS.mdgit clone --depth 1 https://github.com/colbyw5/phenoforgeWrote 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/colbyw5/phenoforge/agents-md)<a href="https://agentmods.dev/instructions/colbyw5/phenoforge/agents-md"><img src="https://agentmods.dev/badge/instructions/colbyw5/phenoforge/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/colbyw5/phenoforge/agents-md"><img src="https://agentmods.dev/badge/instructions/colbyw5/phenoforge/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 | $0.00880 | $0.00880 |
| Opus 5.5 | $0.00352 | $0.00352 |
| Sonnet 5.5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
phenoforge 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 1mo 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Conventions for agentic coding tools working in this repository. The architectural decisions below (layering rule, storage choices, scope boundaries) are settled — treat them as constraints, not suggestions, when proposing changes.
What this is
A retrieval and expansion engine for clinical value sets, exposed over MCP and consumed by a LangGraph agent. Three layers: engine (the contribution), MCP server (thin), agent (application).
Language and style
- Python 3.11+
- PEP 8, enforced by
ruff - Sphinx-style docstrings (
:param:,:type:,:returns:,:rtype:,:raises:) on all public functions, classes, and methods - Full type hints on every signature;
mypy --strictonsrc/ - Pydantic v2 for all data models — no bare dicts crossing module boundaries
- Prefer
pathliboveros.path,httpxoverrequests
Structure
src/phenoforge/
├── engine/ # retrieval, expansion, curated matching, provenance. No I/O to MCP or LLMs.
├── mcp/ # thin MCP server. Tool registration only — no business logic.
├── agent/ # LangGraph graph, state, nodes.
└── eval/ # ontology-aware metrics, benchmark harness.
tests/ # mirrors src/ layout
scripts/ # one-off loaders (vocabulary download, index build)
notebooks/ # Jupyter, exploration only — never pushed to production
data/ # gitignored — Athena downloads, built indices
Layering rule: engine imports nothing from mcp or agent. mcp and agent both
import engine. Violations of this break the whole architectural argument.
Testing
pytest, tests mirror thesrc/layout- Every engine function gets a unit test; no exceptions
- Use a small fixture vocabulary (a few hundred concepts) — do not require the full Athena load to run the test suite
- Eval metrics get property-based tests where the invariant is clear (e.g. distance-weighted score is monotonic in tree distance)
Commands
uv sync # install
ruff check src tests # lint
ruff format src tests # format
mypy src # types
pytest # tests
python scripts/load_vocab.py # build DuckDB from Athena download
python scripts/build_index.py # build LanceDB embedding index
jupyter lab notebooks/ # interactive exploration + eval walkthrough
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.
- 1mo ago First seen · 84 lines · 880 tokens per session scan A fc0fd1e5209b
phenoforge AGENTS.md is an instructions file published in the GitHub repository colbyw5/phenoforge (0 stars, last pushed 13d ago), licensed Apache-2.0. It adds 880 tokens to every session, about $0.0035 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.