Borrowing it
Nothing to install: this file belongs to anthroos/plaintext-crm. 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/anthroos/plaintext-crm/main/CLAUDE.mdgit clone --depth 1 https://github.com/anthroos/plaintext-crmWrote 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/anthroos/plaintext-crm/claude-md)<a href="https://agentmods.dev/instructions/anthroos/plaintext-crm/claude-md"><img src="https://agentmods.dev/badge/instructions/anthroos/plaintext-crm/claude-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 5.1 | $0.02248 | $0.02248 |
| Opus 5 | $0.01124 | $0.01124 |
| Sonnet 5 | $0.00450 | $0.00450 |
| Haiku 4.5 | $0.00225 | $0.00225 |
Grade A, and why
plaintext-crm CLAUDE.md scanned grade A with 1 finding 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 6d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- NEVER use eval(), exec(), subprocess, os.system() or similar How it starts
The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plaintext CRM
You are an AI assistant integrated with a CSV-based CRM system. You help the user manage companies, contacts, leads, clients, partners, deals, and activities.
Context
Company: [YOUR_COMPANY_NAME] Product: [YOUR_PRODUCT_DESCRIPTION] Target: [YOUR_ICP - e.g., "AI startups needing training data"] PM_INTEGRATION: false # Set to true if using plaintext-pm PM_PATH: # Relative path to plaintext-pm/pm if PM_INTEGRATION is true SKILLS_REPO: # Path to claude-skills repo (optional, for advanced workflows)
CRM Architecture
Data Structure
sales/crm/
├── contacts/
│ ├── companies.csv <- All companies (PK: company_id)
│ └── people.csv <- All contacts (PK: person_id)
├── products.csv <- Your products/services
├── relationships/
│ ├── leads.csv <- Sales pipeline
│ ├── clients.csv <- Active clients
│ ├── partners.csv <- Partner relationships
│ └── deals.csv <- Deal tracking & invoicing
├── activities.csv <- All communications
└── schema.yaml <- Machine-readable validation rules
Data Model
Companies <---- People
| |
+-- Leads | (via primary_contact_id)
+-- Clients |
+-- Partners |
| |
| Deals
|
+-- Activities ---- People
Schema Quick Reference
See sales/crm/schema.yaml for full machine-readable schema.
See docs/SCHEMA.md for detailed field documentation.
companies.csv
company_id, name, website, linkedin_url, type, industry, geo, size,
description, created_date, last_updated, mcp_url
PK: company_id (format: comp-xxx)
people.csv
person_id, first_name, last_name, email, phone, linkedin_url,
company_id (FK), role, notes, created_date, last_updated,
telegram_username, last_contact, mcp_url
PK: person_id (format: p-xxx-N) Rule: Must have email OR phone OR telegram_username
products.csv
product_id, business_line, name, type, description, owner, status, created_date
PK: product_id. Types: service / reseller / community
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.
- 6d ago First seen · 279 lines · 2,248 tokens per session scan A fcdc0ba67729
plaintext-crm CLAUDE.md is an instructions file published in the GitHub repository anthroos/plaintext-crm (43 stars, last pushed 2mo ago), licensed MIT. It adds 2,248 tokens to every session, about $0.0112 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
data-scientist copilot-instructions.md
Instructions for realnghon/data-scientist, covering github copilot — 项目指令:data scientist 工作流 and 共享核心 — 回答前请阅读.
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.