ocp CLAUDE.md

ocp CLAUDE.md is an instructions file for coding agents from dtzp555-max/ocp. It costs 8,047 tokens per session, scanned A, original, MIT.

Project-specific coding instructions for the OCP repository, including required checks before changing its server or network-facing code.

In plain words
What is it for?
Use them when starting a task, especially one involving server.mjs, to read the required alignment rules, run the pre-flight command, and follow the correct development process.
Why use it?
They prevent developers from writing code that violates the project's rules or uses the wrong reference material. They also require classifying certain changes before implementation.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/dtzp555-max/ocp/claude-md
Clone the repo
git clone --depth 1 https://github.com/dtzp555-max/ocp

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.

agentmods badge for ocp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dtzp555-max/ocp/claude-md.svg)](https://agentmods.dev/instructions/dtzp555-max/ocp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dtzp555-max/ocp/claude-md"><img src="https://agentmods.dev/badge/instructions/dtzp555-max/ocp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 8,047 This file is loaded in full into every session.
When invoked 8,047 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.08047 $0.08047
Opus 5 $0.04023 $0.04023
Sonnet 5 $0.01609 $0.01609
Haiku 4.5 $0.00805 $0.00805

Measured 6d ago against content hash 57bef5474d29, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ocp 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 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.

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.

CLAUDE.md · 442 lines

How it starts

The opening of the file, as written. The whole thing — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@AGENTS.md @~/.cc-rules/AGENTS.md

OCP Project Session Instructions

WARNING — READ BEFORE WRITING ANY CODE IN THIS REPO

Before touching server.mjs or any network-facing surface, read ./ALIGNMENT.md in full. The constitution is binding. Non-compliant commits are reverted.


Before starting any task

  1. Read ./ALIGNMENT.md. Internalize the five Rules, the scope they are declared under (ALIGNMENT.md:17 — Class A only), and the 2026-04-11 drift lesson.
  2. Run /dev-start <task description> to get a pre-flight plan that incorporates the iron rules, SKILL_ROUTING.md, this file, and ALIGNMENT.md.
  3. If the task touches server.mjs, classify the change (next section) and locate that class's reference — cli.js for Class A, the OpenAI specification section for B.1, the authorizing ADR for B.2 — before drafting any code. No code is written ahead of the evidence.

Classify the change first: Class A or Class B

ALIGNMENT.md's five Rules are not universal. ALIGNMENT.md:17 scopes Rules 1–5 to Class A operations — the cli.js-mirror surface. server.mjs also serves a Class B surface that OCP owns outright, where cli.js is not the wire authority and the governing document is an ADR. Which class the change falls in is therefore the first decision, and it determines which evidence the next section demands.

Classification is a table lookup, not an argument. Class B is a closed, enumerated inventory in ALIGNMENT.md § "Current Class B inventory", plus the Hybrid note immediately after it (ALIGNMENT.md:135, which is where /usage lives — it is not in the table). If the handler you are touching is listed there, it is Class B. You do not get to reclassify an endpoint by arguing for it, and you do not get to declare new surface Class B to avoid a cli.js citation — new Class B surface needs its own ADR (below).

Class Surface Authority Citation
A cli.js-mirror: inbound and outbound /v1/messages, the OAuth bearer machinery, the Anthropic wire call inside /usage. OCP forwards, observes, or multiplexes something cli.js already does. cli.js at the ALIGNMENT.md audit pin. Rules 1–5 apply verbatim. cli.js:NNNN or cli.js vE4 <functionName>
B.1 OpenAI-compatibility: /v1/chat/completions, /v1/models. cli.js cannot speak OpenAI's wire format, by construction. OpenAI's published /v1/chat/completions specification, plus ADR 0006. Spec section URL + ADR 0006
B.2 OCP-administrative: /health, /dashboard, /logs, /status, /settings, /api/keys*, /api/usage, /cache*. Exists to operate the proxy itself. The ADR that authorized the endpoint. The endpoints listed here are grandfathered by ADR 0006 at their v3.16.4 behaviour. Authorizing ADR number
Hybrid /usage — Class A wire call under a Class B synthesis layer. Both, per layer touched. Both, per layer touched

Read the full file on GitHub · 442 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.

  1. 6d ago First seen · 442 lines · 8,047 tokens per session scan A 57bef5474d29

Subscribe to this mod's changes

ocp CLAUDE.md is an instructions file published in the GitHub repository dtzp555-max/ocp (105 stars, last pushed 4d ago), licensed MIT. It adds 8,047 tokens to every session, about $0.0402 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.