Borrowing it
Nothing to install: this file belongs to cmj-hub/claude-evp. 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/cmj-hub/claude-evp/main/AGENTS.mdgit clone --depth 1 https://github.com/cmj-hub/claude-evpWrote 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/cmj-hub/claude-evp/agents-md)<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/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/cmj-hub/claude-evp/agents-md"><img src="https://agentmods.dev/badge/instructions/cmj-hub/claude-evp/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 | $0.00762 | $0.00762 |
| Opus 5.5 | $0.00305 | $0.00305 |
| Sonnet 5.5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
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 18d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Behavior rules for claude-evp
Rules
- Always load brand-config.json + SOUL.md first. Missing either → run the
setupmode (skills/evp/modes/setup.md). - Refuse vague outcomes. "Improve" / "optimize" / "drive growth" — push back with the operator's outcomes-I-will-claim list.
- Refuse made-up proof. Every EVP variant must cite proof from the operator's reservoir, not invented case studies.
- Enforce the 22-word limit. Hard constraint.
- 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.
- Schwartz model is the canon. 5 tiers: unaware / problem-aware / solution-aware / product-aware / most-aware. Refuse to substitute marketing-funnel terms.
- Read the PSP, never invent it. Pain and vocabulary come from
brand-config.psp(published by the psp pack), falling back topsp_drafts.primary. Neither → name the psp pack and its install line (/plugin install psp@gtm-operator-skills, then/psp:psp). - Merge, never overwrite.
brand-config.jsonandSOUL.mdare shared by every pack in the suite. Read the existing file, add or update only this pack's fields (evp_drafts,competitors,primary_outreach_tier,refresh_cadence_days,evp), and leave every other key exactly as it was. Never rewrite the file from the example, never delete another pack's keys. Show the diff and ask before changing a field that already has a value.operatorandicpare shared: fill gaps only. InSOUL.md, touch only this pack's own##sections. - Publish the outreach line. When the operator picks the line for
primary_outreach_tier, write theevpblock:tier,primary,outcome,tradeoff,proof. Downstream packs (cold-email, landing-page, sales-offer, email-sequence) readevp.
What the agent NEVER does
- Generates an EVP without brand-config + SOUL (refuses) Scoring a draft the operator pasted is the exception: score it, say which checks the missing config skipped, then offer setup.
- 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)
- Rewrites
brand-config.jsonorSOUL.mdwholesale, or drops another pack's keys or sections - Writes the
pspblock (that belongs to the psp pack)
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.
- 18d ago Changed · +13 lines · +450 tokens per session 3b649f1e8a24
- 1mo ago First seen · 23 lines · 312 tokens per session scan A 252d53047f8d
claude-evp AGENTS.md is an instructions file published in the GitHub repository cmj-hub/claude-evp (3 stars, last pushed 4d ago), licensed MIT. It adds 762 tokens to every session, about $0.0030 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.