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/elroy-bot/elroy/agents-mdgit clone --depth 1 https://github.com/elroy-bot/elroyWhat 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 | $0.00276 | $0.00276 |
| Opus 5 | $0.00138 | $0.00138 |
| Sonnet 5 | $0.00055 | $0.00055 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
elroy 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.
What it actually says
Agent Instructions for Elroy
Build and Test Commands
IMPORTANT: This project uses just as a command runner. Always use just commands instead of running build/test tools directly.
Tracking work
Common Commands
- Run tests:
just test(NOTpytestorpython -m pytest) - Run specific test:
just test <test_path> - Build:
just build(NOTpython -m buildor similar) - Lint:
just lint - Format:
just format
Finding Available Commands
Run just --list to see all available commands for this project.
Review guidelines
Use CODE_REVIEW.md as the source of truth for code review expectations in this repository.
During review:
- Apply the role, dependency, and validation rules defined in
CODE_REVIEW.md - Do not duplicate or invent competing review standards in review comments
- Treat
just lint,just typecheck, andjust testas required validation before code is ready for review. Do NOT ignore failures even if they are pre-existing
Project Roadmap
Reference ROADMAP.md for current priorities, and update it when completing roadmap items or adding new ones.
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 · 35 lines · 276 tokens per session scan A 65119f217e1a
elroy AGENTS.md is an instructions file published in the GitHub repository elroy-bot/elroy (59 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 276 tokens to every session, about $0.0014 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
MemOS CLAUDE.md
Claude Code instructions for MemTensor/MemOS, covering claude.md, claude code entry, sub-agents and project knowledge.
MemMachine AGENTS.md
AGENTS.md instructions for MemMachine/MemMachine, covering memmachine agent guide, repository orientation, environment setup, build, lint, and test commands and python (repo root).
MemOS AGENTS.md
AGENTS.md instructions for MemTensor/MemOS, covering agents.md, project overview, repository layout, command cheatsheet and core api.
openconcho AGENTS.md
Instructions for offendingcommit/openconcho, covering openconcho, commands, structure, code style and workflows.
LaPis AGENTS.md
Instructions for GeneGulanesJr/LaPis, covering protocols, 1. code & doc retrieval — use memory-code / memory-doc, 2. persistent memory — automatic, when to use the tools and content format.
engram CLAUDE.md
Instructions for techtheist/engram, covering engram — context for claude code, hard rules (locked — don't relitigate without reason), where things go, workflows & sharp edges and now / next (keywords).