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/mrwuss/p21-api-documentation/claude-mdgit clone --depth 1 https://github.com/mrwuss/p21-api-documentationWrote 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/mrwuss/p21-api-documentation/claude-md)<a href="https://agentmods.dev/instructions/mrwuss/p21-api-documentation/claude-md"><img src="https://agentmods.dev/badge/instructions/mrwuss/p21-api-documentation/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 | $0.03909 | $0.03909 |
| Opus 5 | $0.01954 | $0.01954 |
| Sonnet 5 | $0.00782 | $0.00782 |
| Haiku 4.5 | $0.00391 | $0.00391 |
Grade A, and why
p21-api-documentation 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 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project: P21 API Documentation
Comprehensive documentation and working examples for all P21 APIs.
Quick Context
This project provides developer-focused documentation for Prophet 21's integration APIs. All content is based on official Epicor SDK documentation and verified working implementations - no guesses or assumptions.
How to Navigate (read this before opening docs)
The numbered docs are the deep manual — several exceed 1,000 lines. Do not read a whole doc for one task. The routing flow is:
- Read this file (you're here).
- Open docs/INDEX.md — a task → section-anchor map.
- Load only the linked section(s) your task needs.
When editing docs, keep INDEX.md's anchors in sync (renaming a heading breaks its index entry), and add an index row for any new task-worthy section.
APIs Covered
| API | Purpose | Use When | Status |
|---|---|---|---|
| OData | Read-only data access via standard OData protocol | Quick reads, reporting, lookups | Working |
| Transaction API | Stateless bulk data manipulation | Bulk creates, keyed updates/upserts, external integrations | Working |
| Interactive API | Stateful window interactions with business logic | Complex workflows, validation needed | Working |
| Entity API | REST CRUD — /api/entity/ (4 entities) plus other endpoint families (e.g. /api/sales/orders) |
Simple record operations on 4 entities | Working (/api/entity/) |
| Inventory REST API | CRUD on inventory items, multi-company workflows | Item reads, appending locations/suppliers | Working (/api/inventory/parts) |
| Production & Labor | Production orders, labor hours, time entry | Manufacturing workflows, labor tracking | Working (Transaction + Interactive) |
| ui/full (web client) | Drives any web-enabled window by menu class name | The window has no service_name — no TAPI/Interactive route |
Working ({ui}/ui/full/) |
| UDT Service API | CRUD on user-defined tables | Custom table maintenance | Working (/udtservice/api/udtdata/) |
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 · 176 lines · 3,909 tokens per session scan A 107712362b8b
p21-api-documentation CLAUDE.md is an instructions file published in the GitHub repository mrwuss/p21-api-documentation (46 stars, last pushed 4d ago), licensed MIT. It adds 3,909 tokens to every session, about $0.0195 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
onebase CLAUDE.md
Claude Code instructions for ivanarama/onebase, covering claude.md, сборка и запуск, cli + сервер (без cgo) — основной бинарь, gui с нативным окном (cgo + webview2 на windows) and тесты.
mcp-erpnext AGENTS.md
AGENTS.md instructions for Casys-AI/mcp-erpnext, covering agents.md, project overview, project structure & module organization, build, test, and development commands and run all tests (also: deno task test).
go-rest-api-boilerplate copilot-instructions.md
Instructions for vahiiiid/go-rest-api-boilerplate, covering 📋 what is grab?, 🎯 core development principles, 1. environment detection - don't hardcode versions, check go version and check docker version.
SpecFusion CLAUDE.md
Instructions for wxkingstar/SpecFusion, covering specfusion, 项目结构, 开发命令, 安装依赖 and 启动 api 服务（开发模式，热重载）.
balaka CLAUDE.md
Claude Code instructions for artivisi/balaka, covering claude instructions, project overview, current status, key files and development guidelines.
SpecFusion AGENTS.md
Instructions for wxkingstar/SpecFusion, covering specfusion, 项目结构, 开发命令, 安装依赖 and 启动 api 服务（开发模式，热重载）.