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/badass-data-science/pyfit-agentic-polygon-nesting/agents-mdgit clone --depth 1 https://github.com/badass-data-science/pyFit-agentic-polygon-nestingWrote 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/badass-data-science/pyfit-agentic-polygon-nesting/agents-md)<a href="https://agentmods.dev/instructions/badass-data-science/pyfit-agentic-polygon-nesting/agents-md"><img src="https://agentmods.dev/badge/instructions/badass-data-science/pyfit-agentic-polygon-nesting/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 5.1 | $0.04051 | $0.04051 |
| Opus 5 | $0.02025 | $0.02025 |
| Sonnet 5 | $0.00810 | $0.00810 |
| Haiku 4.5 | $0.00405 | $0.00405 |
Grade A, and why
pyFit-agentic-polygon-nesting AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -s https://pypi.org/pypi/<name>/json` — a 404 means available), not How it starts
The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Agent-facing guide to working in this repo. For user-facing docs (CLI usage, job spec format, algorithm explanation, known limitations) see README.md.
What this is
pyFit (directory pyFit-agentic-polygon-nesting; importable package and CLI
command are pyfit/pyfit-mcp, but the PyPI distribution name is
pyfit-agentic-polygon-nesting — see "Naming note" below for why it diverges) is a
general-purpose 2D irregular-polygon nesting (bin-packing) tool: given a set of 2D
shapes and how many of each are needed, it arranges them onto rectangular sheet
stock with minimal wasted material, via a no-fit-polygon (NFP) bottom-left-fill
heuristic. It reads part outlines from DXF files or inline polygons and writes one
DXF per sheet used plus a JSON utilization report.
It was originally a sibling project to pyLair (pyLair-agentic-geodesics, a
geodesic dome calculator) in this same Engineering repo, but has zero code
dependency on it — the only link is file-level (pyLair's cutting-template DXF
output can be fed in as job-spec input). pyLair has since moved to its own repo;
this project is standalone.
Setup
pip install -e ".[test]"
Optional extras: mcp (mcp<2.0 — pinned like pyLair's own mcp extra, since
mcp 2.0.0 removed mcp.server.fastmcp entirely; pyfit/mcp_server.py's
FastMCP/Image imports and tests/test_mcp_server.py both 404 on 2.0.0's new
module layout), and lint (ruff, mypy, types-shapely — what CI runs).
test also pulls in pytest-cov; run pytest --cov=pyfit --cov-report=term-missing
for a coverage report (note pyfit/cli.py will show as ~0% covered even
though tests/test_cli.py exercises it thoroughly — those tests invoke it as
a subprocess, which coverage.py can't see into without extra
COVERAGE_PROCESS_START plumbing this project doesn't bother with; it's a
measurement gap, not an actual testing gap).
Packaging / PyPI readiness
pyproject.toml has PyPI-ready metadata: classifiers, keywords,
[project.urls] (Homepage/Repository/Issues/Changelog, all pointing at this
GitHub repo), and [tool.setuptools.package-data] shipping pyfit/py.typed
(PEP 561 — this package's type hints are meant to be consumed by downstream
type checkers, not just its own CI). Verify packaging changes with python -m build (needs the build package) followed by twine check dist/* (needs
twine) before trusting them — pyproject.toml syntax errors and missing
files don't otherwise surface until an actual publish attempt. Nothing has
been published to PyPI yet; publishing is a separate, deliberate step (not
something to do as a side effect of a metadata change).
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 · 254 lines · 4,051 tokens per session scan A fafbccfde3a4
pyFit-agentic-polygon-nesting AGENTS.md is an instructions file published in the GitHub repository badass-data-science/pyFit-agentic-polygon-nesting (0 stars, last pushed 1mo ago), licensed MIT. It adds 4,051 tokens to every session, about $0.0203 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
archlang AGENTS.md
AGENTS.md instructions for ChanMeng666/archlang, covering agents.md, project overview, project status & where things live (current), standing decisions & iron laws (never re-litigate) and commands.
archlang CLAUDE.md
Claude Code instructions for ChanMeng666/archlang, covering claude.md, orientation (the rest is in agents.md), non-negotiable invariants (break these and ci fails), verify your work the way the tool is used and conventions.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
apex-accelerator vendor-prompting.instructions.md
Vendor prompting best-practice rules for Anthropic Claude and OpenAI GPT-5.6-Terra agents and prompts. Each rule cites a rule ID in the vendor-prompting skill rules.json registry. Validator: npm run lint:vendor-prompting.
autopus-adk GEMINI.md
Gemini CLI instructions for Insajin/autopus-adk, covering autopus-adk harness, 스킬 디렉터리, core guidelines, subagent delegation and file size limit.