read-agents-md

read-agents-md is a skill for Claude Code from aiya000/dotfiles. It costs 64 tokens per session (472 once invoked), scanned A, original, MIT.

An instruction for finding and reading AGENTS.md files from the current directory up to the project root. AGENTS.md files provide guidance for how an agent should work in a codebase.

In plain words
What is it for?
Use it when asked to load or refresh AGENTS.md guidance, and when first accessing files in a directory whose instructions have not yet been read.
Why use it?
It ensures the agent sees the applicable project instructions before accessing files, including instructions in parent directories.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions AGENTS.md.

Good fit Use it when asked to load or refresh AGENTS.md guidance, and when…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aiya000/dotfiles/read-agents-md
Install

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.

Any agent
npx skills add aiya000/dotfiles --skill read-agents-md
Clone the repo
git clone --depth 1 https://github.com/aiya000/dotfiles

Made for: Claude Code.

Wrote 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.

agentmods badge for read-agents-md

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiya000/dotfiles/read-agents-md.svg)](https://agentmods.dev/skills/aiya000/dotfiles/read-agents-md)
Your own site
<a href="https://agentmods.dev/skills/aiya000/dotfiles/read-agents-md"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/read-agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 472 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.00472
Opus 5 $0.00032 $0.00236
Sonnet 5 $0.00013 $0.00094
Haiku 4.5 $0.00006 $0.00047

Measured 7d ago against content hash 94833305d1c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

read-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 7d 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.

.claude_global/skills/read-agents-md/SKILL.md · 35 lines

What it actually says

read-agents-md

Reading AGENTS.md

Read the following files in order (skip any that do not exist):

  1. ~/.dotfiles/AGENTS.global.md — global agent instructions shared across all projects
  2. All AGENTS.md files along the path from the current directory up to the project root (inclusive on both ends)

To find the files for step 2:

  • Determine the project root with git rev-parse --show-toplevel (or treat the current directory as root if not in a git repo)
  • Walk from the current directory up to the project root, collecting each directory that contains an AGENTS.md
  • Read them from outermost (project root) to innermost (current directory)

After reading all found files, say 'AGENTS.md loaded!'

On first access to a file in a directory

The first time you access (read or write) any file in a directory whose files you have not touched yet in this session, read that directory's AGENTS.md if it exists and has not been loaded yet.

Rules:

  • "First access" means the first time in the session you read or write any file inside that directory
  • Only the AGENTS.md directly in that immediate directory is loaded — do not search parent directories here
  • If the directory has no AGENTS.md, nothing is loaded
  • Each directory's AGENTS.md is loaded at most once per session
  • When you load a new directory's AGENTS.md this way, also re-read every AGENTS.md you have already loaded in this session (including the current directory's), so all of them stay fresh in context
Changes

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.

  1. 7d ago First seen · 35 lines · 64 tokens per session scan A 94833305d1c4

Subscribe to this mod's changes

read-agents-md is a skill published in the GitHub repository aiya000/dotfiles (19 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 472 once invoked, about $0.0003 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.