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/erstanai/erstan-agent-tools-beta/agents-mdgit clone --depth 1 https://github.com/erstanai/erstan-agent-tools-betaWrote 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/erstanai/erstan-agent-tools-beta/agents-md)<a href="https://agentmods.dev/instructions/erstanai/erstan-agent-tools-beta/agents-md"><img src="https://agentmods.dev/badge/instructions/erstanai/erstan-agent-tools-beta/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 | $0.00288 | $0.00288 |
| Opus 5 | $0.00144 | $0.00144 |
| Sonnet 5 | $0.00058 | $0.00058 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
erstan-agent-tools-beta 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 4d 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
Contributor guidance
This is a public, allowlisted beta distribution repository. Keep it small and safe.
- Never add credentials, customer data, production traces, private diagnostics, local environment files, or generated caches.
- Keep the Codex and Claude plugin names and versions aligned with the package version and both marketplace entries.
- Keep the hosted MCP URL exactly
https://api-qa.erstan.com/v1/mcpunless an intentional release changes it everywhere. - Keep the plugin and marketplace identity exactly
erstan-betaso it can be installed beside the productionerstanplugin without a name collision. - Do not submit this temporary repository to a public plugin directory. Beta access is enforced by Erstan OAuth and server-side access policy.
- Do not add static authentication headers, key fields, or token environment variables. Authentication is OAuth through the host.
- Do not add
.app.jsonwithout a real registered OpenAI app identifier and a deliberate publication review. - Put maintainer CLI tools and offline diagnostics in the separate toolkit, never in this plugin. Repository-owned distribution sync automation may stay here, but user-facing optimization belongs in hosted-MCP Skills rather than npm CLI commands.
- Run
npm run verify, the Codex plugin validator, all seven skill validators, andclaude plugin validate .before release.
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.
- 4d ago First seen · 25 lines · 288 tokens per session scan A ab366ebab640
erstan-agent-tools-beta AGENTS.md is an instructions file published in the GitHub repository erstanai/erstan-agent-tools-beta (0 stars, last pushed 6d ago), licensed Apache-2.0. It adds 288 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 2026-08-31.
Other instructions, from other repositories
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
hatch3r CLAUDE.md
Claude Code instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
ken CLAUDE.md
Claude Code instructions for townsendmerino/ken, covering claude.md, what this is, repository ownership (read this first), commands and embedding parity & golden fixtures (now in aikit).
cortex AGENTS.md
AGENTS.md instructions for tools-for-agents/cortex, covering agents.md — cortex, setup, the rules this repo is built on, tests and ci.
CustomerNewsletter copilot-instructions.md
Instructions for briancl2/CustomerNewsletter, covering copilot instructions, mission, always read first, core workflow and rules.