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/jaswdr/faker/claude-mdgit clone --depth 1 https://github.com/jaswdr/fakerWhat 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 | $0.00511 | $0.00511 |
| Opus 5 | $0.00255 | $0.00255 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
faker CLAUDE.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 yesterday.
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.
What it actually says
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository Overview
This is the faker library for Go - a data generation library for creating fake/mock data for testing, database seeding, and anonymization. It's heavily inspired by PHP's Faker.
The library requires Go >= 1.22 (as per go.mod) and uses Go's math/rand/v2 package for random generation.
Core Architecture
The library follows a modular design where each data type has its own file and corresponding test file:
faker.go- Main Faker struct and GeneratorInterface that provides thread-safe random generation- Each data category (e.g.,
person.go,address.go,internet.go) implements its own struct with methods - All generators are accessed through the main Faker instance created with
faker.New() - The library uses struct tags (
fake:"...") to support generating fake data directly into structs
Key pattern: Each generator returns a new instance that shares the same underlying random generator for consistency and thread safety.
Common Commands
Testing
# Run all tests
go test ./...
# Run tests with verbose output
go test -v ./...
# Run tests with benchmarks
go test -v -bench=. ./...
# Run a specific test
go test -run TestPersonName -v
# Run tests multiple times (as done in CI)
for i in 1 2 3; do go test -v -bench=. ./... && break || if [ $i -eq 3 ]; then exit 1; fi; done
Code Quality
# Format code
gofmt -w .
# Check for issues
go vet ./...
# Build the library
go build ./...
Note: There are known struct tag syntax issues in struct_test.go (lines 239, 248, 274) that cause go vet warnings. These are intentional test cases for malformed tags.
Development Workflow
- The library is purely functional with no external dependencies beyond Go standard library
- Each data generator should have comprehensive tests in its corresponding
_test.gofile - Thread safety is handled at the Faker struct level through the threadSafeRand wrapper
- When adding new generators, follow the existing pattern of creating a new struct type with methods
- The main branch is
master(notmain)
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.
- yesterday First seen · 61 lines · 511 tokens per session scan A d22a73a4e9c1
faker CLAUDE.md is an instructions file published in the GitHub repository jaswdr/faker (644 stars, last pushed 1mo ago), licensed MIT. It adds 511 tokens to every session, about $0.0026 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 2026-09-01.
Other instructions, from other repositories
awesome-go AGENTS.md
AGENTS.md instructions for avelino/awesome-go, covering awesome-go · llm contribution guide, project snapshot, when modifying the awesome list, coding guidelines and testing & validation.
cockroach CLAUDE.md
Claude Code instructions for cockroachdb/cockroach, covering claude.md, cockroachdb development environment, essential commands, build package ./pkg/util/log and build the tests in package ./pkg/util/log.
thunderid AGENTS.md
Instructions for thunder-id/thunderid, covering project overview, where to look next, search hygiene, validation ladder and product name rules.
thunderid copilot-instructions.md
Instructions for thunder-id/thunderid: All project coding standards, conventions, and guidelines are defined in AGENTS.md.
awesome-go copilot-instructions.md
Copilot instructions for avelino/awesome-go, a project described as: A curated list of awesome Go frameworks, libraries and software.
thunderid CLAUDE.md
Instructions for thunder-id/thunderid, a project described as: ThunderID is a high-performance, open-source identity stack designed for developers to secure and manage access for humans, AI agents, and machines through fully composable identity flows.