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/hyper-mcp-rs/hyper-mcp/agents-mdgit clone --depth 1 https://github.com/hyper-mcp-rs/hyper-mcpWrote 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/hyper-mcp-rs/hyper-mcp/agents-md)<a href="https://agentmods.dev/instructions/hyper-mcp-rs/hyper-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/hyper-mcp-rs/hyper-mcp/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 | $0.00410 | $0.00410 |
| Opus 5 | $0.00205 | $0.00205 |
| Sonnet 5 | $0.00082 | $0.00082 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
hyper-mcp 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 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.
What it actually says
AGENTS.md
Project Overview
hyper-mcp is a Rust-based Model Context Protocol server that loads and manages plugins (WASM binaries) at runtime.
Tooling
- defuddle — Fetches web pages and converts them to clean Markdown. Use when you need content from a URL.
- context7 — Queries documentation for any library or framework. Always resolve the library ID first via
resolve_library_id, then query viaquery_docs. - sentrux — Enforces architectural constraints defined in
.sentrux/rules.toml. Runcheck_rulesbefore submitting changes to ensure compliance.
Commits
Always sign commits with -s (git commit -s). Never bypass git hooks. Resolve any lefthook errors from pre-commit or pre-push hooks before finishing.
Testing
Unit tests are mandatory for new functionality. Every new feature, module, or non-trivial change must be accompanied by tests. Do not add code without tests.
Rust code must pass cargo fmt and cargo clippy. Run both before submitting changes.
Session Constraints
Sentrux session checks are mandatory. Always call session_start at the beginning of every session to establish a quality baseline. At the end of a session, call session_end to compare the final state against the baseline.
Quality drops must be called out. If session_end reports any degradation (modularity, acyclicity, depth, equality, or redundancy), document the specific violations and explain why they occurred. Do not ignore or silently accept quality declines.
Rescan boundaries. Call rescan whenever you make edits that may affect the quality signals (file creation, deletion, or structural changes). The scan picks up file changes since the last scan and re-evaluates the quality baseline. Always rescan after meaningful changes before running session_end to ensure the final comparison reflects the actual state of the codebase.
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 · 30 lines · 410 tokens per session scan A 73a850b8de1c
hyper-mcp AGENTS.md is an instructions file published in the GitHub repository hyper-mcp-rs/hyper-mcp (880 stars, last pushed 4d ago), licensed Apache-2.0. It adds 410 tokens to every session, about $0.0020 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
wassette AGENTS.md
Instructions for microsoft/wassette, covering agent guide for wassette, start here, agent skills and repository requirements.
wassette copilot-instructions.md
Instructions for microsoft/wassette: Follow the repository-wide guidance in AGENTS.md, which links to the canonical contributor documentation and focused agent skills.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
Instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).