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/halo-dev/cli/agents-mdgit clone --depth 1 https://github.com/halo-dev/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 | $0.02091 | $0.02091 |
| Opus 5 | $0.01045 | $0.01045 |
| Sonnet 5 | $0.00418 | $0.00418 |
| Haiku 4.5 | $0.00209 | $0.00209 |
Grade A, and why
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 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file follows the open AGENTS.md convention from https://agents.md. Treat it as the agent-facing README for this repository: use it to get oriented, make changes in the existing style, and run the right checks before handing work back.
Project Overview
@halo-dev/cli is a TypeScript, ESM-based CLI for managing Halo instances.
- Runtime: Node.js >= 22
- Published binary:
halo - Source entry:
src/cli.ts - Local development entry:
tsx src/cli.ts - Build output:
dist/cli.mjs - Package manager: Vite+ wraps the underlying package manager; prefer
vpcommands for project tooling.
The root CLI currently exposes these business areas:
authpostsingle-pagesearchpluginthemeattachmentbackupmomentcommentnotificationcompletion
Setup Commands
- Install dependencies after pulling changes:
vp install - Run the CLI from source:
vp exec tsx src/cli.ts --help - Run a command from source:
vp exec tsx src/cli.ts <command> ... - Build the published CLI:
vp build
Do not use pnpm, npm, or yarn directly for dependency management unless the
user explicitly asks for it. Vite+ is the project toolchain wrapper.
Validation Commands
Use the smallest useful check while iterating, then run broader checks before finishing a meaningful change.
- Fast TypeScript regression check:
pnpm typecheck - Lint:
vp lint - Full project check:
vp check - Tests:
vp test - Build:
vp build
pnpm typecheck is intentionally kept here because it is currently the fastest
way to catch TypeScript regressions in this CLI. For Vite+, do not run commands
such as vp vitest or vp oxlint; use vp test and vp lint.
Vite+ Rules
This project uses Vite+, a unified toolchain built on top of Vite, Rolldown, Vitest, tsdown, Oxlint, Oxfmt, and Vite Task.
- Run
vp helporvp <command> --helpfor command details. - Use
vp run <script>when you need apackage.jsonscript whose name conflicts with a Vite+ built-in command. - Use
vp dlxfor one-off package binaries. - Import Vite+ APIs from
vite-plus, for exampleimport { defineConfig } from "vite-plus";. - Import test APIs from
vite-plus/test, for exampleimport { expect, test, vi } from "vite-plus/test";. - Do not add direct dependencies on Vitest, Oxlint, Oxfmt, or tsdown just to use their CLIs or APIs.
- Type-aware linting is available through
vp lint --type-aware; do not addoxlint-tsgolintfor that purpose.
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 · 229 lines · 2,091 tokens per session scan A 9634f288f948
cli AGENTS.md is an instructions file published in the GitHub repository halo-dev/cli (29 stars, last pushed 2mo ago), licensed MIT. It adds 2,091 tokens to every session, about $0.0105 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
ClawKeeper copilot.instructions.md
Copilot instructions for SafeAI-Lab-X/ClawKeeper, covering openclaw codebase patterns, tech stack, anti-redundancy rules, source of truth locations and formatting utilities (src/infra/).
skills AGENTS.md
Instructions for bastos/skills, covering agent skills, commits, creating a skill, structure and skill.md format.
skills CLAUDE.md
Instructions for bastos/skills, covering agent skills, commits, creating a skill, structure and skill.md format.
autocontext CLAUDE.md
Instructions for greyhaven-ai/autocontext, covering claude.md, project overview, repository layout, commands and setup.
agentregistry copilot-instructions.md
Instructions for agentregistry-dev/agentregistry, covering github copilot instructions and keeping the pr description up-to-date.
loom CLAUDE.md
Instructions for cosmix/loom, covering claude.md, project overview, build commands, architecture and source layout (loom/src/).