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.
npx agentmods add instructions/etrebels/claude-code-growth-os/agents-mdgit clone --depth 1 https://github.com/etrebels/claude-code-growth-osWrote 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/etrebels/claude-code-growth-os/agents-md)<a href="https://agentmods.dev/instructions/etrebels/claude-code-growth-os/agents-md"><img src="https://agentmods.dev/badge/instructions/etrebels/claude-code-growth-os/agents-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 | $0.03192 | $0.03192 |
| Opus 5 | $0.01596 | $0.01596 |
| Sonnet 5 | $0.00638 | $0.00638 |
| Haiku 4.5 | $0.00319 | $0.00319 |
Grade A, and why
claude-code-growth-os 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 4d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Claude Code Growth OS
Instructions for AI coding agents working on this repository. For project overview, conventions, and session protocol, see CLAUDE.md.
Purpose
This is a public, generic growth-OS kit built on Claude Code — a markdown + bash system for running marketing, sales, product, and retention as one motion. It ships as a reusable template. For Edwin's personal live-state (pipeline, customers, priorities), see etrebels/langoptima-growth-os.
No code. No build system. Markdown playbooks in ops/, rituals as slash commands in .claude/commands/, skills in .claude/skills/.
Repository Map
claude-code-growth-os/
├── CLAUDE.md # Project config, conventions, session protocol
├── AGENTS.md # This file
├── README.md # Public-facing overview and quick-start
├── CHANGELOG.md # Version history
├── CONTRIBUTING.md # Contribution guidelines
├── SECURITY.md # Security policy
├── CODE_OF_CONDUCT.md # Community standards
├── LICENSE # MIT license
├── THIRD-PARTY-NOTICES.md # Credits for adapted third-party patterns
├── inbox/
│ └── notes.md # /capture staging buffer — raw notes, triaged later
├── ops/ # LIVE STATE LAYER — mutable, routines read/write
│ ├── pipeline.md # Live deal board (one line per open deal)
│ ├── customers.md # Post-sale account health
│ ├── priorities.md # This week's priority + today's Top 3
│ ├── daily-log.md # Append-only field-capture log
│ ├── feedback-log.md # Cross-function feedback loops (sales→marketing, post-sale→product)
│ ├── roadmap-signals.md # Field/retention signals → product
│ ├── chokepoints.md # The few narrow dependencies most revenue flows through
│ ├── direction-register.md # Live standing direction — outranks a conflicting rule
│ └── icp.md # Ideal customer profile definition
├── demo/ # Fictional-data sandbox for testing rituals
│ ├── pipeline.md
│ ├── customers.md
│ ├── priorities.md
│ ├── daily-log.md
│ ├── feedback-log.md
│ ├── roadmap-signals.md
│ ├── support-tickets.md
│ └── meetings/ # Sample meeting notes
├── docs/ # Reference documentation
│ ├── operating-model.md # Bowtie, six handoffs, the one number (NRR)
│ ├── methodology.md # Why this system is built the way it is
│ ├── designing-loops.md # Why the loop, not the prompt, is the thing you design
│ ├── connecting-a-crm.md # CRM projection loop and find-or-create mechanics
│ ├── first-ritual.md # Getting-started guide
│ ├── launch-scrub-checklist.md # Pre-launch safety checklist
│ ├── why-align.md # Why sales + marketing alignment matters
│ ├── why-brand.md # Why brand investment matters
│ ├── principles-from-history.md # Operating principles sourced from history
│ ├── principles-from-science.md # Operating principles sourced from science
│ ├── principles-from-the-field.md # Operating principles from running the motion itself
│ └── assets/ # Diagrams, images
├── .github/
│ └── workflows/ # CI: scheduled deterministic checks + shellcheck on hooks
├── .claude/
│ ├── settings.json # Claude Code settings (hooks, permissions)
│ ├── settings.local.example.json # Template for local secrets config (gitignored when copied)
│ ├── commands/ # Slash commands — the daily rituals
│ │ ├── morning-briefing.md # Recap yesterday, surface priorities, set today's top three
│ │ ├── midday-checkin.md # Mid-day reset — done, slipping, what to protect
│ │ ├── end-of-day.md # Daily-log entry + tomorrow's Top 3
│ │ ├── weekly-review.md # Weekly patterns + next week's one priority
│ │ ├── retention-report.md # Monthly NRR/GRR readout from the customer book
│ │ ├── capture.md # Drop a raw note now, triage it later
│ │ ├── reconcile.md # Catch drift when multiple sessions write the same files
│ │ └── demo-briefing.md # The morning ritual run on the fictional demo/ data
│ ├── hooks/ # Guardrails that fire on events
│ │ ├── session-start.sh # Surfaces ops/priorities.md + feedback-log signals
│ │ ├── pre-compact.sh # Re-injects priorities + latest log before compaction
│ │ ├── protect-files.sh # Blocks writes to secrets and .env files
│ │ ├── verify-after-change.sh # Post-change link check + optional project verifier (advisory)
│ │ ├── stop-reminder.sh # Nudges /end-of-day until today is logged
│ │ ├── pre-commit-guard.sh # Git pre-commit hook — blocks likely secrets
│ │ └── web-bootstrap.sh # Installs shellcheck on cloud/web sessions only
│ ├── rules/ # Standing constraints every session honors
│ │ ├── README.md # Rules overview and conventions
│ │ ├── crm-usage.md # CRM-over-MCP: docs-first protocol, write-authority guardrails
│ │ └── todo-single-source.md # One to-do list, rendered one way (the canonical spec)
│ ├── scheduling/ # Running rituals on a clock
│ │ ├── README.md # Three-layer scheduling overview (local / cloud / CI)
│ │ └── cloud-routines.md # Cloud Routines runbook (Anthropic-hosted)
│ ├── scripts/
│ │ ├── verify.sh.example # Template for your own post-change verifier
│ │ └── checks/
│ │ └── growth-os-checks.sh # Deterministic checks run by CI / scheduled jobs
│ └── skills/ # Reusable growth skills (one directory per skill)
│ ├── account-health/ # Post-sale health review for a named account
│ ├── calendar-followup/ # Draft follow-up based on today's calendar events
│ ├── churn-save/ # Recovery play for a red/amber account
│ ├── cold-outreach/ # Generate a targeted cold outreach sequence
│ ├── content-repurpose/ # Repurpose a piece of content across channels
│ ├── event-to-pipeline/ # Work a conference or event into booked calls
│ ├── example-skill/ # Template / reference skill
│ ├── expansion-signal/ # Work a ready-to-grow account and hand it to sales
│ ├── follow-up/ # Draft a follow-up for a named deal or contact
│ ├── inbox-digest/ # Summarize and triage inbound messages
│ ├── lead-qualify/ # Score a lead against the ICP fit check
│ ├── marketing-feedback/ # Surface MARKETING-ACTION tags from ops/
│ ├── meeting-prep/ # Prep brief for a named meeting or prospect
│ ├── onboarding-handoff/ # CS handoff document for a new customer
│ ├── product-signal/ # Surface FEATURE-REQUEST / RETENTION-RISK tags
│ ├── qbr-prep/ # Value-realization review brief for a customer
│ ├── retention-feedback/ # Surface RETENTION-RISK tags for review
│ ├── status-update/ # Draft a status update for a named deal or account
│ ├── support-signal/ # Cluster support tickets into ranked product themes
│ └── triage/ # Triage open items across ops/ files
└── .mcp.json.example # Template for MCP server config (copy → .mcp.json, gitignored)
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.
- 4d ago First seen · 187 lines · 3,192 tokens per session scan A c43bb218fabe
claude-code-growth-os AGENTS.md is an instructions file published in the GitHub repository etrebels/claude-code-growth-os (20 stars, last pushed 4d ago), licensed MIT. It adds 3,192 tokens to every session, about $0.0160 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.
Other instructions, from other repositories
forbotsake AGENTS.md
Instructions for forbotsake/forbotsake, covering forbotsake, skills, getting started, key files (created by skills) and installation.
forbotsake CLAUDE.md
Instructions for forbotsake/forbotsake, covering forbotsake — marketing skills for ai coding agents, skill routing, pipeline, platform research (inline) and how it works.
marketingskills AGENTS.md
AGENTS.md instructions for coreyhaines31/marketingskills, covering agents.md, repository overview, repository structure, build / lint / test commands and versioning.
pruna-skills AGENTS.md
AGENTS.md instructions for PrunaAI/pruna-skills, covering pruna skills (agent notes), how it works, clarification (library-wide), install and layout.
marketingskills CLAUDE.md
Claude Code instructions for coreyhaines31/marketingskills, a project described as: Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.
sandy CLAUDE.md
Instructions for jamestelfer/sandy, covering claude.md, voice, what is sandy, project layout and dev commands.