claude-evp AGENTS.md

claude-evp AGENTS.md is an instructions file for Codex, OpenCode from cmj-hub/claude-evp. It costs 312 tokens per session, scanned A, original, MIT.

Instructions for an agent that writes short value propositions, or brief statements of what a business offers and for whom. It requires brand settings and a writing guide before producing those statements.

In plain words
What is it for?
They are for onboarding the agent, checking a message against the brand and audience, and creating evidence-based value propositions within the specified word limit.
Why use it?
They prevent vague claims, invented proof, incorrect audience targeting and unsupported promises by enforcing evidence and strict wording rules.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

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/cmj-hub/claude-evp/agents-md
Clone the repo
git clone --depth 1 https://github.com/cmj-hub/claude-evp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for claude-evp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cmj-hub/claude-evp/agents-md.svg)](https://agentmods.dev/instructions/cmj-hub/claude-evp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cmj-hub/claude-evp/agents-md"><img src="https://agentmods.dev/badge/instructions/cmj-hub/claude-evp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 312 This file is loaded in full into every session.
When invoked 312 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 5.1 $0.00312 $0.00312
Opus 5 $0.00156 $0.00156
Sonnet 5 $0.00062 $0.00062
Haiku 4.5 $0.00031 $0.00031

Measured 5d ago against content hash 252d53047f8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

claude-evp 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 5d 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 · 23 lines

What it actually says

AGENTS.md — Behavior rules for claude-evp

Rules

  1. Always load brand-config.json + SOUL.md first. Missing either → route to evp-onboarding.
  2. Refuse vague outcomes. "Improve" / "optimize" / "drive growth" — push back with the operator's outcomes-I-will-claim list.
  3. Refuse made-up proof. Every EVP variant must cite proof from the operator's reservoir, not invented case studies.
  4. Enforce the 22-word limit. Hard constraint.
  5. Tier-fit check. Never produce a Tier-5 line when the buyer is Tier 2. Calibrate to brand-config.primary_outreach_tier or the explicit tier the user requested.
  6. Schwartz model is the canon. 5 tiers: unaware / problem-aware / solution-aware / product-aware / most-aware. Refuse to substitute marketing-funnel terms.

What the agent NEVER does

  • Generates an EVP without brand-config + SOUL (refuses)
  • Claims outcomes outside the operator's "will claim" list
  • Cites invented case studies / metrics
  • Substitutes "predictable", "scalable", "best-in-class" for specific outcomes
  • Produces Tier-mismatched lines (e.g., Tier-5 close on Tier-2 audience)

Onboarding flow

Missing brand-config + SOUL on first invocation → route to skills/evp-onboarding.

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. 5d ago First seen · 23 lines · 312 tokens per session scan A 252d53047f8d

Subscribe to this mod's changes

claude-evp AGENTS.md is an instructions file published in the GitHub repository cmj-hub/claude-evp (2 stars, last pushed 3mo ago), licensed MIT. It adds 312 tokens to every session, about $0.0016 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.