Borrowing it
Nothing to install: this file belongs to ricktaylor/hardy. 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/ricktaylor/hardy/main/AGENTS.mdgit clone --depth 1 https://github.com/ricktaylor/hardyWrote 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/ricktaylor/hardy/agents-md)<a href="https://agentmods.dev/instructions/ricktaylor/hardy/agents-md"><img src="https://agentmods.dev/badge/instructions/ricktaylor/hardy/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/ricktaylor/hardy/agents-md"><img src="https://agentmods.dev/badge/instructions/ricktaylor/hardy/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 | $0.02180 | $0.02180 |
| Opus 5.5 | $0.00872 | $0.00872 |
| Sonnet 5.5 | $0.00436 | $0.00436 |
| Haiku 4.5 | $0.00218 | $0.00218 |
Grade A, and why
hardy 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 2mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hardy — agent guide
Hardy is a performant, RFC 9171-compliant, extensible BPv7 Delay-Tolerant Networking (DTN) implementation, written in async Rust. It is a Cargo workspace on the stable toolchain; the edition and MSRV are defined in the workspace Cargo.toml ([workspace.package]). See README.md for the full feature list and the complete crate inventory.
Workspace layout
The workspace is split into many small crates. The ones you will touch most often:
cbor/— RFC 8949 canonical CBOR codec (no_std).bpv7/— RFC 9171 bundle format: parsing, building, editing, BPSec (no_std).bpa/— the Bundle Processing Agent library: routing, dispatch, filter pipeline, RIB, storage/CLA/service registries.bpa-server/— the binary that wires the BPA together; closed-source extensions register against the unmodifiedbpacrate via public traits.eid-patterns/,async/,proto/,otel/— supporting libraries.*-storage/— pluggable storage backends (localdisk, sqlite, postgres, s3).tcpclv4/,file-cla/,bibe/— convergence layers;tvr/— Time-Variant Routing agent.tools/,bpv7/tools/,cbor/tools/— CLI tools (bp,bundle,cbor).
tests/interop/mtcp is excluded from the workspace and built separately.
Build, test, lint
Proto-dependent crates require protoc (CI installs protobuf-compiler). Common commands:
cargo build --release # build everything
cargo test --workspace --all-features # run the test suite
cargo fmt # format
cargo clippy --all-targets --all-features # lint
A change is not done until these CI gates pass — run them before handing work back:
cargo fmt --check
cargo clippy --locked --all-targets --all-features -- -D warnings
cargo test --locked --all-features --workspace
Clippy is enforced with -D warnings: no warnings are allowed to land.
Code style — the essentials
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.
- 2mo ago Changed · +3 lines · +319 tokens per session 8a22fe721605
- 2mo ago First seen · 85 lines · 1,861 tokens per session scan A 1d5f6565e5bd
hardy AGENTS.md is an instructions file published in the GitHub repository ricktaylor/hardy (24 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,180 tokens to every session, about $0.0087 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 2026-08-30.
hardy AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hardy AGENTS.mdricktaylor/hardy | Instructions file | 24 | 2d ago | Apache-2.0 | A | 2,180 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |