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/autohandai/code-cli/agents-mdgit clone --depth 1 https://github.com/autohandai/code-cliWhat 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 | $0.01679 | $0.01679 |
| Opus 5 | $0.00839 | $0.00839 |
| Sonnet 5 | $0.00336 | $0.00336 |
| Haiku 4.5 | $0.00168 | $0.00168 |
Grade A, and why
code-cli 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 2d 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file helps Autohand understand how to work with this project.
You are a critical, staff-level software engineer writing production-grade TypeScript for CLI tools. Your work must be built with reliability, maintainability, and scale in mind.
1M users depend on this software. Code quality, test coverage, and runtime stability are mandatory.
We use Ink for TUI.
Required version: >=7.0.0
React version: >=19
These versions must never be downgraded.
Ink docs: https://www.npmjs.com/package/ink https://github.com/vadimdemedes/ink/tree/master/examples
Project Overview
- Language: TypeScript
- Framework: React + Ink
- Package Manager: bun
- Test Framework: Vitest
- Build Tool: tsup
Current Repository Architecture
src/core/agent runtime split (current)
The interactive runtime is now split across src/core/agent into focused layers:
src/core/agent.ts—AutohandAgentpublic surface and top-level execution entrypoint.src/core/agent/AgentLifecycleRunner.ts— run mode orchestration (interactive, command mode, initialization, cleanup, signal handling).src/core/agent/InputTurnCoordinator.ts— input capture, queueing, ESC/Ctrl+C handling.src/core/agent/AgentDependencyComposer.ts— dependency wiring (initializeAgentDependencies) and runtime host setup.src/core/agent/AgentContextRuntime.ts— session bootstrap and context snapshot construction.src/core/agent/SystemPromptBuilder.ts— system prompt assembly and prompt-shaping.src/core/agent/ReactLoopRunner.ts— tool-call driven execution loop and response orchestration.src/core/agent/InstructionRunner.ts— single-instruction orchestration and completion flow.src/core/agent/AgentCommandRuntime.ts— slash command handling and execution.src/core/agent/AgentProjectOperations.ts— project-level operations (diff/commit/bootstrap quality hooks).src/core/agent/AgentUIRuntime.ts— composer/TTY/prompt UI state updates and status messaging.src/core/agent/AgentSessionAccounting.ts+src/core/agent/AgentToolOutputRuntime.ts— tool accounting, logging, and output shaping.src/core/agent/ProviderConfigManager.ts/WorkspaceFileCollector.ts/AgentProjectOperations.ts— feature-specific adapters and support services.
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.
- 2d ago First seen · 277 lines · 1,679 tokens per session scan A e560a112c40e
code-cli AGENTS.md is an instructions file published in the GitHub repository autohandai/code-cli (181 stars, last pushed 5d ago), licensed Apache-2.0. It adds 1,679 tokens to every session, about $0.0084 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
neuron-ai AGENTS.md
Instructions for neuron-core/neuron-ai, covering neuron ai - project overview, the mental model: neuron is a composable workflow, development commands, architecture and modules.
neuron-ai CLAUDE.md
Instructions for neuron-core/neuron-ai, covering project overview, code standards, think before coding, simplicity first and surgical changes.
crush AGENTS.md
AGENTS.md instructions for charmbracelet/crush, covering crush development guide, project overview, architecture, key dependency roles and key patterns.
dive CLAUDE.md
Instructions for deepnoodle-ai/dive, covering claude.md, project overview, commands, architecture and core types.
Zettelgarden CLAUDE.md
Instructions for Zettelgarden/Zettelgarden, covering claude.md, project overview, development commands, frontend (zettelkasten-front/) and backend (go-backend/).
Zettelgarden AGENTS.md
Instructions for Zettelgarden/Zettelgarden, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.