Borrowing it
Nothing to install: this file belongs to Lumio-Research/hermes-agent-rs. 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/Lumio-Research/hermes-agent-rs/main/AGENTS.mdgit clone --depth 1 https://github.com/Lumio-Research/hermes-agent-rsWrote 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/lumio-research/hermes-agent-rs/agents-md)<a href="https://agentmods.dev/instructions/lumio-research/hermes-agent-rs/agents-md"><img src="https://agentmods.dev/badge/instructions/lumio-research/hermes-agent-rs/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/lumio-research/hermes-agent-rs/agents-md"><img src="https://agentmods.dev/badge/instructions/lumio-research/hermes-agent-rs/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 | $0.05716 | $0.05716 |
| Opus 5 | $0.02858 | $0.02858 |
| Sonnet 5 | $0.01143 | $0.01143 |
| Haiku 4.5 | $0.00572 | $0.00572 |
Grade A, and why
hermes-agent-rs 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 9d 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 — 619 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes Agent (Rust) — Development Guide
Instructions for AI coding assistants and developers working on the hermes-agent-rust codebase.
Parity status: 13/13 scoped items completed. See
README.mdfor the full tracker.
Build & Test
cargo build --release # Binary at target/release/hermes
cargo test --workspace # 1,428 tests, all crates
cargo test -p hermes-parity-tests # Parity fixture tests only
cargo clippy --workspace --all-targets # Lint (target: -D warnings)
cargo fmt --all --check # Format check
# Eval framework with real agent loop
cargo build -p hermes-eval --features agent-loop
Artifact 锁:Blocking waiting for file lock on artifact directory
终端里 cargo run 与编辑器里的 rust-analyzer(cargo check)会争用同一 target/ artifact 锁,表现为长时间阻塞。
仓库内缓解(已提交):
.vscode/settings.json:"rust-analyzer.cargo.targetDir": true—— 让 rust-analyzer 使用target下独立子目录做检查,与命令行cargo build/cargo run分离(改完后请重载窗口 / 重启 rust-analyzer)。scripts/hermes:若已存在target/debug/hermes,则直接执行该二进制,避免每次cargo run抢锁;需要强制走 cargo 时:HERMES_USE_CARGO=1 ./scripts/hermes …。首次可chmod +x scripts/hermes,或始终sh scripts/hermes …。
若仍卡住:确认没有其它终端在长时间 cargo build,必要时结束残留 cargo 进程后再试。
Project Structure
hermes-agent-rust/
├── Cargo.toml # Workspace root — 16 crates, pinned deps
├── AGENTS.md # This file (loaded by Hermes at runtime)
├── PARITY_PLAN.md # 8-week parity roadmap
├── Dockerfile # Multi-stage release build
├── scripts/
│ ├── hermes # 优先 target/debug/hermes,减轻与 RA 的 artifact 锁竞争
│ └── record_fixtures.py # Fixture recording script
└── crates/
├── hermes-core/ # Shared types, traits, error hierarchy
├── hermes-agent/ # Agent loop, LLM providers, memory plugins, context
├── hermes-tools/ # Tool registry, dispatch, 30 tool backends
├── hermes-gateway/ # Message gateway, 17 platform adapters
├── hermes-cli/ # CLI/TUI binary, slash commands, app state
├── hermes-config/ # Config loading, YAML/JSON/env merging, validation
├── hermes-intelligence/ # Smart routing, prompt builder, usage pricing, display
├── hermes-skills/ # Skill management, file store, hub client, versioning
├── hermes-environments/ # Terminal backends (Local/Docker/SSH/Daytona/Modal/Singularity)
├── hermes-cron/ # Cron scheduling and persistence
├── hermes-mcp/ # Model Context Protocol client/server
├── hermes-acp/ # Agent Communication Protocol
├── hermes-eval/ # Evaluation framework (Runner, BenchmarkAdapter, Verifier)
├── hermes-server/ # HTTP/WebSocket API server
├── hermes-telemetry/ # OpenTelemetry + Prometheus metrics
└── hermes-parity-tests/ # Golden fixture tests for behavioral parity
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.
- 9d ago First seen · 619 lines · 5,716 tokens per session scan F 7934e937511b
hermes-agent-rs AGENTS.md is an instructions file published in the GitHub repository Lumio-Research/hermes-agent-rs (90 stars, last pushed 2mo ago), licensed MIT. It adds 5,716 tokens to every session, about $0.0286 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.