What is skills CLAUDE.md?

A set of instructions for maintaining skills in the GrowthBook repository. GrowthBook is software for running product experiments and analysing their results.

Verify API requests, endpoints, statistical guidance, lifecycle claims, and other skill content against the canonical GrowthBook code before editing.

It helps keep skill documentation aligned with the repository's source code and prevents outdated API details or recommendations from being published.

How growthbook/skills configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to growthbook/skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/growthbook/skills/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/growthbook/skills

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/growthbook/skills/claude-md.svg)](https://agentmods.dev/instructions/growthbook/skills/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/growthbook/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/growthbook/skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 6,811 This file is loaded in full into every session.

When invoked 6,811 The same file — it is already loaded in full.

Security scan D 2 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.06811	$0.06811
Opus 5	$0.03406	$0.03406
Sonnet 5	$0.01362	$0.01362
Haiku 4.5	$0.00681	$0.00681

Measured 2d ago against content hash ca54d48e7851, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade D, and why

skills CLAUDE.md scanned grade D with 2 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- **When you do grant another binary, prefer literal full-command patterns over wildcards.** `Bash(chmod 600 ~/.config/growthbook/.env)` is a much narrower grant than `Bash(chmod *)` — the latter would allow `chmod 777 ~

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

- **When you do grant another binary, prefer literal full-command patterns over wildcards.** `Bash(chmod 600 ~/.config/growthbook/.env)` is a much narrower grant than `Bash(chmod *)` — the latter would allow `chmod 777 ~

CLAUDE.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guide for working on this repo. Read this before adding or modifying a skill.

⚠ Always verify against the GrowthBook source of truth

This is the most important rule in this file.

Every API payload, endpoint path, statistical recommendation, lifecycle claim, or "best practice" in any SKILL.md must be cross-checked against the canonical GrowthBook sources. The skills sit downstream of decisions made there, and have already drifted once — a 2026-05 audit found three broken endpoints, contradictory stats framing, and a regex claim that disagreed with the actual handler. Never write or change a guardrail, payload shape, or recommendation in a skill without verifying it against at least one of these:

These live in a local checkout of the GrowthBook monorepo, referred to below as <growthbook>. It's typically cloned as a sibling of this repo (i.e. ../growthbook); if you don't find it there, ask where the checkout lives rather than guessing.

Back-end source code — <growthbook>/packages/back-end/src/api/ and <growthbook>/packages/shared/src/validators/. The Zod validators here are the final authority on payload shapes, required fields, and accepted enum values. If docs and code disagree, the code wins.

Docusaurus docs — <growthbook>/docs/docs/. The canonical source for statistical methodology, lifecycle guidance, and "best practices we learned the hard way." Map of where things live:

Topic	Doc path
Feature flag basics, environments, rules	`docs/features/`
Stale-flag detection criteria	`docs/features/stale-detection.mdx`
Approval & publishing flows	`docs/features/publishing-and-approval-flows.mdx`
Experiment lifecycle, A/A tests, durations	`docs/experiments.mdx`, `docs/running-experiments/`
Stats engine (Bayesian default, frequentist)	`docs/statistics/overview.mdx`
SRM, peeking, sequential testing	`docs/statistics/sequential.mdx`, `docs/statistics/power.mdx`
Multiple-comparison correction	`docs/statistics/multiple-corrections.mdx`
Six data-quality checks for analysis	`docs/experimentation-analysis/experiment-results.mdx`
Decision framework (ship/roll back/review)	`docs/experimentation-analysis/decision-framework.mdx`
Goal vs. secondary vs. guardrail metrics	`docs/metrics/`, `docs/experimentation-analysis/`
Sticky bucketing (commercial)	`docs/sticky-bucketing.mdx`
Bandits	`docs/bandits/`
Common pitfalls (SRM causes, bots, etc.)	`docs/kb/experiments/troubleshooting-experiments.mdx`, `docs/faq.mdx`
API conventions, auth, rate limit	`docs/api-overview.mdx`

Read the full file on GitHub · 299 lines

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.

2d ago Changed · +2 lines · +35 tokens per session ca54d48e7851
5d ago Changed · +3 tokens per session 34fd75d4be5f
7d ago First seen · 297 lines · 6,773 tokens per session scan D b32b9997209c

Subscribe to this mod's changes

skills CLAUDE.md is an instructions file published in the GitHub repository growthbook/skills (20 stars, last pushed 2d ago), licensed MIT. It adds 6,811 tokens to every session, about $0.0341 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

skills: Instructions file for Claude Code