Borrowing it
Nothing to install: this file belongs to aayushmau5/eva. 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/aayushmau5/eva/main/AGENTS.mdgit clone --depth 1 https://github.com/aayushmau5/evaWrote 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/aayushmau5/eva/agents-md)<a href="https://agentmods.dev/instructions/aayushmau5/eva/agents-md"><img src="https://agentmods.dev/badge/instructions/aayushmau5/eva/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/aayushmau5/eva/agents-md"><img src="https://agentmods.dev/badge/instructions/aayushmau5/eva/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 | $0.00463 | $0.00463 |
| Opus 5.5 | $0.00185 | $0.00185 |
| Sonnet 5.5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
eva 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.
What it actually says
AGENTS.md
Before Committing / After Writing Code
Always run mix precommit after code changes are complete and before committing. This catches compile warnings, unused deps, formatting issues, and test failures in one pass.
Packages
Two Mix projects live here, and the boundary between them is a namespace:
. |
:eva |
the host — sessions, the agent loop, providers, tools, extension loading |
core/ |
:eva_core |
the contract an extension is written against |
Everything in core/ is Eva.Core.* and lives under core/lib/eva/core/. Everything in
the host is Eva.*. So Eva.Core.Bus and Eva.Core.Extension.Spec are contract;
Eva.Extension.Loader and Eva.Cluster are host. The two interleave — Eva.Agent.*,
Eva.Cluster.* and Eva.Extension.* each have modules on both sides — so when renaming or
moving anything in those trees, check which package owns it rather than matching a prefix.
The one namespace that is neither: Eva.Extension.<Name> is where an extension itself
must live (Eva.Core.Extension.namespace/1 enforces it). Third-party code, not core's.
Extensions are separate repos. MCP is at ../eva-mcp and depends on eva_core through a
sparse git checkout of core/; set EVA_CORE_PATH there to build it against a local Eva.
test/eva/mcp_node_test.exs is the only test that crosses into it, and skips if it is
absent.
Architecture
Keep modules cohesive — each module does one thing well. StreamState owns SSE buffering and delta accumulation; OpenAICompatible owns the GenServer lifecycle and HTTP streaming for Open-AI compatible APIs; Sse owns raw SSE line parsing. Don't cram unrelated concerns into one module.
Code flows through functions. Prefer Elixir's control-flow constructs — with, case, cond, Enum.reduce/3, and the pipe operator — over deeply nested if/else.
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 · 35 lines · 463 tokens per session scan A 59cda2d817a8
eva AGENTS.md is an instructions file published in the GitHub repository aayushmau5/eva (7 stars, last pushed 2mo ago), licensed MIT. It adds 463 tokens to every session, about $0.0019 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.
eva AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| eva AGENTS.mdaayushmau5/eva | Instructions file | 7 | 2mo ago | MIT | A | 463 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |