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/dtzp555-max/ocp/claude-mdgit clone --depth 1 https://github.com/dtzp555-max/ocpWrote 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/dtzp555-max/ocp/claude-md)<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>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 | $0.08047 | $0.08047 |
| Opus 5 | $0.04023 | $0.04023 |
| Sonnet 5 | $0.01609 | $0.01609 |
| Haiku 4.5 | $0.00805 | $0.00805 |
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.
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.mjsor any network-facing surface, read./ALIGNMENT.mdin full. The constitution is binding. Non-compliant commits are reverted.
Before starting any task
- 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. - Run
/dev-start <task description>to get a pre-flight plan that incorporates the iron rules,SKILL_ROUTING.md, this file, andALIGNMENT.md. - If the task touches
server.mjs, classify the change (next section) and locate that class's reference —cli.jsfor 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 |
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.
- 6d ago First seen · 442 lines · 8,047 tokens per session scan A 57bef5474d29
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.
Other instructions, from other repositories
lyra-ai CLAUDE.md
Instructions for ahkedia/lyra-ai, covering claude code — lyra (lyra-ai), mandatory: git before/after work and project context.
lyra-ai AGENTS.md
Instructions for ahkedia/lyra-ai, covering agents.md - your workspace, git workflow (cursor, claude code, automation), two repos — public/private split (mandatory routing), session startup and memory.
inference-x AGENTS.md
Instructions for coeusyk/inference-x, covering openspec agent instructions for inferencex, working agreement, agent tooling (mandatory — token efficiency), two command paths only — no third and rtk proxy (rtk-ai/rtk).
inference-x CLAUDE.md
Instructions for coeusyk/inference-x, covering claude.md — inferencex, tooling (mandatory every session), two paths only — no third, token-savior mcp (if present) and why.
bridgenode-skill AGENTS.md
AGENTS.md instructions for bridgenode-ai/bridgenode-skill, covering agents.md — bridgenode skill & examples, what bridgenode is, how an agent pays (x402 flow, 4 steps), quick start (buyer side) and curl — full flow in examples/.
bridgenode-mcp AGENTS.md
AGENTS.md instructions for bridgenode-ai/bridgenode-mcp, covering agents.md, commands, structure, conventions and rules.