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/lootlog/monorepo/agents-mdgit clone --depth 1 https://github.com/lootlog/monorepoWrote 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.
[](https://agentmods.dev/instructions/lootlog/monorepo/agents-md)<a href="https://agentmods.dev/instructions/lootlog/monorepo/agents-md"><img src="https://agentmods.dev/badge/instructions/lootlog/monorepo/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01485 | $0.01485 |
| Opus 5 | $0.00743 | $0.00743 |
| Sonnet 5 | $0.00297 | $0.00297 |
| Haiku 4.5 | $0.00148 | $0.00148 |
Grade A, and why
monorepo 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 3d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI agent instructions
These instructions apply to every workspace unless a closer AGENTS.md
overrides a rule for its subtree.
Authority and required context
Apply instructions in this order:
- the closest
AGENTS.mdto the file being changed; - parent
AGENTS.mdfiles up to this root; - canonical repository documents linked below;
- repository skills in
.agents/skills; - generic or external skills;
- lint, tests, and CI as mechanical enforcement.
A local instruction may strengthen or replace a root rule only when it states the exception explicitly.
Read the documents relevant to the change:
PRODUCT.md— target product, priorities, and non-goals.CONTEXT.md— canonical domain terms.ARCHITECTURE.md— current system, target contracts, and known gaps.docs/adr/README.md— accepted architecture decisions and their lifecycle.SECURITY.md— mandatory for auth, authorization, API, gateway, user content, data, public endpoints, and external integrations.DESIGN.md— canonical visual system for public and product surfaces.apps/web/design-guideline.md— web app UI contract.
PRODUCT.md and target sections in ARCHITECTURE.md are design constraints,
not proof that a feature already exists. Do not describe target behavior as
implemented until code and verification agree.
CodeGraph
In repositories indexed by CodeGraph (a .codegraph/ directory exists at the
repo root), use it before grep/find or reading source files when you need to
understand or locate code:
- MCP: use
codegraph_explorefor symbols, source, and call paths, orcodegraph_nodefor one symbol or source file. - Shell: use
codegraph explore "<question>"orcodegraph node <symbol-or-file>.
If .codegraph/ does not exist, skip CodeGraph. Indexing is the user's decision.
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.
- 3d ago First seen · 159 lines · 1,485 tokens per session scan A 3bc27620313d
monorepo AGENTS.md is an instructions file published in the GitHub repository lootlog/monorepo (10 stars, last pushed 3d ago), licensed MIT. It adds 1,485 tokens to every session, about $0.0074 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
HA-Websocket-Stripper CLAUDE.md
Instructions for GabrielGoldsteinAnidea/HA-Websocket-Stripper, covering ha websocket stripper — project context, what this is / why it exists, why this approach (history — don't re-litigate), mechanism and allowlist computation.
fonline-tla AGENTS.md
Instructions for cvet/fonline-tla, covering fonline: the life after - agent instructions, what this project is, repository orientation, build and verify and engine update workflow.
fonline-tla copilot-instructions.md
Instructions for cvet/fonline-tla: Follow the repository agent instructions in /AGENTS.md.
anki-eco AGENTS.md
AGENTS.md instructions for ikkz/anki-eco, covering agents.md, project overview, environment and package management, common commands and validation strategy.
rustycore AGENTS.md
AGENTS.md instructions for alseif0x/rustycore, covering agents.md, project and source of truth, reference priority, current checkpoint and working an issue (session kickoff).
rustycore CLAUDE.md
Claude Code instructions for alseif0x/rustycore: The operating guide for this repository lives in AGENTS.md — a single source shared by Claude Code, Codex, and other agents. The line below imports it so Claude Code loads the full guide automatically. Edit AGENTS.md, not this file.