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/tygryso/hypotree/copilot-instructionsgit clone --depth 1 https://github.com/tygryso/hypotreeWrote 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/tygryso/hypotree/copilot-instructions)<a href="https://agentmods.dev/instructions/tygryso/hypotree/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/tygryso/hypotree/copilot-instructions.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 | $0.01749 | $0.01749 |
| Opus 5 | $0.00874 | $0.00874 |
| Sonnet 5 | $0.00350 | $0.00350 |
| Haiku 4.5 | $0.00175 | $0.00175 |
Grade C, and why
hypotree copilot-instructions.md scanned grade C 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 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **NEVER run `rm -rf` on the belief-state database** before or after `pytest`. This wipes the belief-state and is completely unnecessary — all test fixtures create temp DBs via `tmp_path`. How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hypotree — Project Instructions
Platform & Environment
- OS: Linux, macOS and Windows.
eval.shis bash-only (WSL or Git Bash on Windows); everything else runs natively on all three. - Languages: Python 3.10+
- Frameworks/Libraries: MCP (modelcontextprotocol), Pydantic, SciPy (Beta distributions), SQLite (stdlib)
- Eval/Plotting: Pandas, NumPy, Matplotlib, Seaborn
- Tooling: uv, pytest, ruff, mypy
- Version Control: Git (GitHub)
Refactoring & Code Quality
- Migrations and backward compatibility are required. The project is open-source and entering production. SQLite schema changes must bump the version and upgrade old databases automatically. Deprecation warnings should precede removals by at least one minor version. Never break existing belief-state databases without a migration.
- Prefer generalization. When implementing a feature, look for opportunities to generalize. Enhance and consolidate logic proactively rather than adding narrow one-off code.
- Maintain inline comments. Keep and improve inline code comments that describe why something exists or what a non-obvious block does. Add brief logic descriptions where they aid comprehension. Never reference plan phase numbers, step numbers, or plan names in comments — comments must be self-contained, descriptive, and meaningful without any external context.
Testing & Linting Discipline
- Always use
uv run— never system Python or pip. This project usesuvfor all environment management. Commands must be prefixed withuv runto use the correct virtual environment. - Modified code requires verification. Any modified class, function, or variable within a file requires a full
pytestrun on that module/file plusruffon that file. No exceptions — the edit is not complete until both pass.- Tests:
uv run pytest <test_file> -x -q - Linter:
uv run ruff check <file> - Format:
uv run ruff format <file> - Type check:
uv run mypy src/hypotree/
- Tests:
- New code requires new tests. Any new function, class, or method must have a corresponding new
pytesttest written for it before the task is considered done. The new test must pass alongsideruffon the new and changed files. - No untested code is shipped. If you add code and do not write a test for it, you have failed the task. Period.
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 · 89 lines · 1,749 tokens per session scan C cbe27eddc032
hypotree copilot-instructions.md is an instructions file published in the GitHub repository tygryso/hypotree (12 stars, last pushed 14d ago), licensed MIT. It adds 1,749 tokens to every session, about $0.0087 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
OpenCode-GraphAgent CLAUDE.md
Instructions for LeXwDeX/OpenCode-GraphAgent, covering claude.md, what this is, commands, quality gates and build & codegen.
matryca-plumber AGENTS.md
Instructions for MarcoPorcellato/matryca-plumber, covering agents.md — matryca plumber instruction router, audience map, instruction loading strategy, always-on working agreements and rule and skill routing.
zenflow AGENTS.md
Instructions for zendev-sh/zenflow, covering agents.md - zenflow, commands, architecture, key rules and coordinator and messaging.
matryca-plumber CLAUDE.md
Instructions for MarcoPorcellato/matryca-plumber, covering code audit — code intelligence, always do, never do, resources and cli.
Waggle-mcp AGENTS.md
Instructions for Abhigyan-Shekhar/Waggle-mcp, covering repository agent rules, custom rules and waggle automatic memory.
junjo AGENTS.md
Instructions for mdrideout/junjo, covering junjo platform agents.md, developer philosophy, scope and complexity, repository ownership and boundary rules.