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/echovic/blade-code/agents-mdgit clone --depth 1 https://github.com/echoVic/blade-codeWrote 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/echovic/blade-code/agents-md)<a href="https://agentmods.dev/instructions/echovic/blade-code/agents-md"><img src="https://agentmods.dev/badge/instructions/echovic/blade-code/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 | $0.01038 | $0.01038 |
| Opus 5 | $0.00519 | $0.00519 |
| Sonnet 5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
blade-code 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 yesterday.
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Always respond in Chinese.
Project Overview
Blade Code is a modern AI-powered coding assistant with CLI + Web UI, built with React + Ink (CLI) and React + Vite (Web), using TypeScript.
Quick Commands
# Development
bun run dev # Start CLI dev mode (watch)
bun run dev:web # Start CLI + Web server
bun run build # Build CLI
# Running
blade # Start interactive CLI
blade web # Start Web UI (opens browser)
blade serve # Start headless server
# Testing & Quality
bun run test:all # Run all tests
bun run lint # Run linter
bun run type-check # TypeScript type checking
Architecture
Monorepo Structure
Blade/
├── packages/
│ ├── cli/ # blade-code - CLI core (npm package)
│ │ └── src/
│ │ ├── agent/ # Stateless Agent core
│ │ ├── tools/ # Tool system (builtin, execution, registry)
│ │ ├── server/ # Web server (Hono)
│ │ ├── mcp/ # MCP protocol support
│ │ ├── context/ # Context management
│ │ ├── config/ # Configuration management
│ │ ├── ui/ # Terminal UI (React + Ink)
│ │ ├── store/ # State management (Zustand)
│ │ ├── services/ # Service layer (Chat, Session, etc.)
│ │ ├── services/pi/ # pi-ai runtime adapter
│ │ ├── schema/ # TypeBox runtime wrapper
│ │ ├── commands/ # CLI subcommands (serve, web, mcp, etc.)
│ │ ├── prompts/ # Prompt templates
│ │ ├── slash-commands/ # Slash commands
│ │ ├── skills/ # Skills system
│ │ ├── hooks/ # Hooks system
│ │ └── blade.tsx # Entry point
│ └── vscode/ # blade-vscode - VSCode extension
├── docs/ # User documentation (Docsify)
└── .blade/ # Project-level config
Key Design Principles
- Stateless Agent: Agent doesn't store session state; all state passed via context
- Tool System: Unified tool registration, execution, and validation with TypeBox schemas
- Permission Control: Three-level permission system (allow/ask/deny)
- Session Management: Multi-session support with resume and fork capabilities
- pi-ai Runtime: Single LLM abstraction layer; model metadata from catalog, not hardcoded
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.
- yesterday First seen · 106 lines · 1,038 tokens per session scan A e27d17cd98ae
blade-code AGENTS.md is an instructions file published in the GitHub repository echoVic/blade-code (178 stars, last pushed today), licensed MIT. It adds 1,038 tokens to every session, about $0.0052 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 2026-09-03.
Other instructions, from other repositories
zypher-agent CLAUDE.md
Instructions for corespeed-io/zypher-agent, covering claude.md, development commands, code quality, architecture overview and monorepo structure.
deepthonk AGENTS.md
AGENTS.md instructions for linxule/deepthonk: DeepThonk is a provider-neutral, OpenDeepThink-style reasoning optimizer exposed as a TypeScript CLI and MCP server.
trpc-agent-go AGENTS.md
AGENTS.md instructions for trpc-group/trpc-agent-go, covering agents.md, project overview, engineering principles, go design conventions and implementation workflow.
better-chatbot AGENTS.md
AGENTS.md instructions for keinsaasforever/better-chatbot, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
zhin zhin-plugin.instructions.md
Instructions for zhinjs/zhin, covering zhin plugin runtime authoring, package contract, convention directories, imports and native typescript and command routes.
agnix typescript.instructions.md
Instructions for agent-sh/agnix, covering typescript instructions and guidelines.