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/jel-ll/file_utils/agents-mdgit clone --depth 1 https://github.com/JEL-LL/file_utilsWhat 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 | $0.00719 | $0.00719 |
| Opus 5 | $0.00360 | $0.00360 |
| Sonnet 5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
file_utils 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Conventions for AI agents working in this repo
This file documents the working conventions any AI agent (or human) must follow
when making changes in the file_utils MCP project. Read it before starting
work. See SPEC.md for the design and TODO.md for the
phased implementation plan.
1. Always use uv
This project is managed with uv. Do not call
python, pip, or pytest directly — always go through uv so the correct
environment and dependencies (from pyproject.toml) are used.
uv installs to C:\Users\<you>\.local\bin (added to PATH by the installer).
A newly opened terminal will have uv / uvx on PATH; an already-open terminal
may need to be reopened first. If uv is not yet installed, install it with the
official Astral installer:
powershell -ExecutionPolicy ByPass -Command "irm https://astral.sh/uv/install.ps1 | iex"
Common commands:
| Task | Command |
|---|---|
| Run the server | uv run server.py |
| Run the test suite | uv run --extra dev pytest |
| Run tests quietly | uv run --extra dev pytest -q |
| Add a dependency | uv add <package> |
| Sync the environment | uv sync --extra dev |
Note: system commands are issued in cmd, not PowerShell (except the one-off
uvinstall command above, which uses PowerShell explicitly).
2. Check in changes after each completed task
After each task/phase from TODO.md is complete and verified
(tests green via uv run --extra dev pytest), commit the changes to version
control before moving on. Keep commits scoped to one logical task so history maps
cleanly onto the phased plan.
Typical flow once a task is done:
git add -A
git commit -m "Phase N: <short description of what was completed>"
Guidelines:
- Commit only after the relevant tests pass.
- Use a clear, present-tense message referencing the phase/task.
- Update the corresponding checkbox in
TODO.mdin the same commit. - Do not bundle unrelated changes into a single commit.
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 · 79 lines · 719 tokens per session scan A c6a6e9ab9590
file_utils AGENTS.md is an instructions file published in the GitHub repository JEL-LL/file_utils (0 stars, last pushed 21d ago), licensed MIT. It adds 719 tokens to every session, about $0.0036 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 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.