agents-md

Description

AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.

What it can do

Reach level 1 — reads What does this mean? →

Can see: the system prompt · subagent spawns · Read calls

Raw API calls (7) +

• $.env.get
• $.fs.ancestors
• $.session.cwd
• $.session.root
• $.telemetry.log
• $.telemetry.mark
• $.ui.log

Static check passed on Claude Code 2.1.289.

Install

Check the repo for the exact name.

Details

Repository

dipthong7119/ttcs_k8s4_n5

Path in repo

frontend/skillfrontend/mods/agents-md

License

Unknown

Last updated

Oct 3, 2026

First seen

Oct 4, 2026

Last scanned

Oct 6, 2026

Related mods — reach level 1

• ruflo-ruos ★ 76,337
• openviking-memory ★ 39,271
• cc-arcade--davila7 ★ 32,551
• 2048 ★ 32,551