Borrowing it
Nothing to install: this file belongs to ogerly/AAMS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ogerly/AAMS/main/AGENTS.mdgit clone --depth 1 https://github.com/ogerly/AAMSWrote 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/ogerly/aams/agents-md)<a href="https://agentmods.dev/instructions/ogerly/aams/agents-md"><img src="https://agentmods.dev/badge/instructions/ogerly/aams/agents-md/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.
<a href="https://agentmods.dev/instructions/ogerly/aams/agents-md"><img src="https://agentmods.dev/badge/instructions/ogerly/aams/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00723 | $0.00723 |
| Opus 5.5 | $0.00289 | $0.00289 |
| Sonnet 5.5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
AAMS 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 2mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file is read automatically by GitHub Copilot, Cursor, Claude Code, OpenAI Codex, Windsurf, Aider, Continue.dev, and most other AI coding agents.
This repository uses AAMS — an agent-contract standard for autonomous work.
Execute now. No confirmation needed.
- Read
.agent.json— your workspace contract - Read
READ-AGENT.md— full project context and session rules - Check state before executing:
- IF
WORKING/WORKPAPER/does not exist or is empty → Executeagent_contract.on_first_entry - IF
WORKING/WORKPAPER/exists and contains workpapers → Executeagent_contract.on_session_start
- IF
You MUST
- Follow the agent contract in
READ-AGENT.md - Create a workpaper in
WORKING/WORKPAPER/at session start - Query
WORKING/MEMORY/for prior context before starting work - Complete the workpaper (file protocol + decisions + next steps) at session end
- Ingest the workpaper into
WORKING/MEMORY/before closing
You MUST NOT
- Write secrets, tokens, or credentials into any workpaper, whitepaper, or manifest
- Delete files in
WORKING/— only create and move - Skip the file protocol in workpapers
Before Creating Any Directory or File
- NEVER create utility/tool/script folders in the project root
- Check
WORKING/structure first —WORKING/TOOLS/is the designated location for helper scripts, templates, and dev utilities - Only create root-level folders if they serve a direct production purpose (e.g.,
src/,public/,dist/) - Before executing any tool: validate its root-anchoring does not point outside
WORKING/ - If a tool uses
Path(__file__).resolve().parent.parentor similar offset paths:- Verify it still resolves to the correct root for its current location
- If uncertain: ask before executing
Beispiel: Ein Python-Skript das früher in /tools/ lag und jetzt in /WORKING/TOOLS/ liegt, braucht einen angepassten Root-Pointer. Ein Offset von .parent.parent zeigt fälschlich auf den Agent-Memory statt auf das Projekt.
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.
- 2mo ago First seen · 74 lines · 723 tokens per session scan A 0d37fc4d0137
AAMS AGENTS.md is an instructions file published in the GitHub repository ogerly/AAMS (7 stars, last pushed 1mo ago), licensed MIT. It adds 723 tokens to every session, about $0.0029 per session on Opus 5.5. 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.
AAMS AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| AAMS AGENTS.mdogerly/AAMS | Instructions file | 7 | 1mo ago | MIT | A | 723 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |