evc AGENTS.md

A cross-platform instruction file for coding-agent tools such as Claude Code, Cursor, Codex CLI, and Gemini CLI. It explains which configuration files each tool reads and sets shared working rules.

In plain words
What is it for?
Use it to configure agent instructions, point agents to shared project guidance, require content staging before publishing, and prevent automatic external posting without approval.
Why use it?
It keeps agent behavior consistent across different coding tools and makes project instructions easier to apply in each environment.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/saigonxiii/evc/agents-md
Clone the repo
git clone --depth 1 https://github.com/SaigonXIII/evc

Made for: Codex, OpenCode.

Per session 250 This file is loaded in full into every session.
When invoked 250 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00250 $0.00250
Opus 5 $0.00125 $0.00125
Sonnet 5 $0.00050 $0.00050
Haiku 4.5 $0.00025 $0.00025

Measured 2d ago against content hash 5d8fd1177a21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evc 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.

AGENTS.md · 26 lines

What it actually says

EVC — Cross-Platform Agent Config

This file provides instructions for non-Claude Code agent harnesses (Cursor, Codex CLI, Gemini CLI).

For Claude Code

Claude Code reads CLAUDE.md and .claude/commands/*.md automatically. No additional configuration needed.

For Cursor

Copy .claude/commands/*.md to .cursor/rules/ and rename as needed. Cursor uses rules files instead of commands.

For Codex CLI

Codex reads AGENTS.md (this file) as its primary instruction source. The commands in .claude/commands/ can be referenced as prompts.

For Gemini CLI

Gemini reads GEMINI.md if present. Copy CLAUDE.md to GEMINI.md for equivalent behavior.


Universal Instructions (for any harness)

  1. Read SOUL.md for operating principles
  2. Load brand/canon-rules.json before writing any content
  3. Check content-engine/memory/lessons.md for accumulated knowledge
  4. Stage all content in staging/ before external publish
  5. Never auto-post to external channels without explicit approval
Changes

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.

  1. 2d ago First seen · 26 lines · 250 tokens per session scan A 5d8fd1177a21

Subscribe to this mod's changes

evc AGENTS.md is an instructions file published in the GitHub repository SaigonXIII/evc (56 stars, last pushed 2mo ago), licensed MIT. It adds 250 tokens to every session, about $0.0013 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.