notify-instruction-file-loaded

notify-instruction-file-loaded is a skill for Claude Code, Codex from aiya000/dotfiles. It costs 43 tokens per session (325 once invoked), scanned A, original, MIT.

An instruction that tells the agent to announce when it has loaded a CLAUDE.md or AGENTS.md file. These files contain instructions for how the agent should work in a project.

In plain words
What is it for?
Use it immediately after reading a CLAUDE.md or AGENTS.md file, with a different message for global and project-local files.
Why use it?
It makes instruction loading visible, so you know which project or global guidance has just been read.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions AGENTS.md.

Good fit Use it immediately after reading a CLAUDE.md or AGENTS.md file, with a different message for global and project-local files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aiya000/dotfiles/notify-instruction-file-loaded
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 notify-instruction-file-loaded
Clone the repo
git clone --depth 1 https://github.com/aiya000/dotfiles

Made for: Claude Code, Codex.

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 notify-instruction-file-loaded

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiya000/dotfiles/notify-instruction-file-loaded/github.svg)](https://agentmods.dev/skills/aiya000/dotfiles/notify-instruction-file-loaded)
Your own site
<a href="https://agentmods.dev/skills/aiya000/dotfiles/notify-instruction-file-loaded"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/notify-instruction-file-loaded/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for notify-instruction-file-loaded

Your own site · 80×15
<a href="https://agentmods.dev/skills/aiya000/dotfiles/notify-instruction-file-loaded"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/notify-instruction-file-loaded.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 325 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 $0.00043 $0.00325
Opus 5 $0.00022 $0.00162
Sonnet 5 $0.00009 $0.00065
Haiku 4.5 $0.00004 $0.00032

Measured 9d ago against content hash 7fa0c028517a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

notify-instruction-file-loaded 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 9d 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/notify-instruction-file-loaded/SKILL.md · 30 lines

What it actually says

notify-instruction-file-loaded

Say the appropriate loaded message based on the path of the instructions file that was just read.

Behavior

Determine the message based on the file path:

Condition Message
Path is ~/.claude/CLAUDE.md or resolves to it Global CLAUDE.md loaded!
Path is {project-root}/.claude/CLAUDE.md or any other CLAUDE.md Local CLAUDE.md loaded!
Path is ~/AGENTS.md or ~/AGENTS.global.md Global AGENTS.md loaded!
Path is any other AGENTS.md (project subdirectory, etc.) Local AGENTS.md loaded!

Classification Rules

  • Global vs Local: If the file lives under the user's home directory config (~/.claude/) or is the home-directory-level AGENTS.md / AGENTS.global.md → Global. Otherwise → Local.
  • CLAUDE vs AGENTS: Determined by the file name (CLAUDE.md → CLAUDE, AGENTS.md or AGENTS.global.md → AGENTS).

Does Not

  • Read or modify any files
  • Do anything other than say the single loaded message
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. 9d ago First seen · 30 lines · 43 tokens per session scan A 7fa0c028517a

Subscribe to this mod's changes

notify-instruction-file-loaded is a skill published in the GitHub repository aiya000/dotfiles (19 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 325 once invoked, about $0.0002 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.