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/agentrhq/authsome/agents-mdgit clone --depth 1 https://github.com/agentrhq/authsomeWhat 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 | $0.02475 | $0.02475 |
| Opus 5 | $0.01238 | $0.01238 |
| Sonnet 5 | $0.00495 | $0.00495 |
| Haiku 4.5 | $0.00248 | $0.00248 |
Grade A, and why
authsome 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents (Claude Code, Codex, Copilot, etc.) when working with this repository.
Commands
Always use uv run to execute commands — do not use python, python3, pip, or bare tool names directly.
# Install in editable mode (required before running anything)
uv pip install -e ".[dev]"
# Run all tests
uv run pytest
# Run a single test file
uv run pytest tests/test_client.py
# Run a single test by name
uv run pytest tests/test_client.py::test_login_pkce -v
# Run tests with coverage
uv run pytest --cov=authsome
Run linting and type checks:
# Lint and auto-fix
uv run ruff check --fix src/ tests/
# Format
uv run ruff format src/ tests/
# Type check
uv run ty check src/
The CLI entry point after install:
uv run authsome onboard
uv run authsome login github
uv run authsome provider list
Engineering principles
For the full set of contribution guidelines, design principles, and AI-assisted development practices, see CONTRIBUTING.md. Everything in that document applies to AI agents as well as human contributors.
These rules govern all changes to this codebase — apply them without exception.
YAGNI. Implement only what the current task demands. Don't build for hypothetical future requirements.
Use trusted libraries over reinventing. Reach for a well-maintained dependency before writing your own crypto, HTTP client, or token parser.
Deep modules over shallow ones. Prefer a small surface area with rich internals over many thin wrappers. More files is not more modular.
Composition over inheritance. Prefer small collaborators wired together through explicit dependencies over inheritance hierarchies. Use inheritance only when there is a real subtype relationship and composition would make the design less clear.
Single responsibility and separation of concerns. Auth authenticates. Vault stores credentials. CLI presents output. A flow must not write to storage; storage must not know about OAuth. If a function is hard to name, it's doing too many things.
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.
- 2d ago First seen · 164 lines · 2,475 tokens per session scan A 321e8725000d
authsome AGENTS.md is an instructions file published in the GitHub repository agentrhq/authsome (84 stars, last pushed 1mo ago), licensed MIT. It adds 2,475 tokens to every session, about $0.0124 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
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
barkeep AGENTS.md
Instructions for iannuttall/barkeep, covering agent notes, product rules, repo map, commands and app structure.
blz AGENTS.md
Instructions for outfitter-dev/blz, covering blz repository instructions for ai agents, important, working memory, use blz and 🚀 quick start for agents.
CrewClaw AGENTS.md
Instructions for staruhub/CrewClaw, covering agents.md, project, boundaries (charter, 2026-07-10), commands and employee package rules.
fenestra AGENTS.md
Instructions for richer-richard/fenestra, covering building fenestra uis as an agent, the loop, driving a real app: the harness, json scenarios (no recompile) and asserting structure (accessibility tree).
Agent-Memory-Bridge AGENTS.md
Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.