DCGP CLAUDE.md

A mount-point instruction file for the DCGP repository. It directs coding agents to the main rule files—HARDRULES.md, AGENTS.md, and DCGP-SPEC.md—and identifies a verification script as the final check when documents and code disagree.

In plain words
What is it for?
Use it at the start of work in the DCGP repository to find the governing rules, understand which files to edit, and check the repository’s verified state.
Why use it?
It prevents agents from editing a file that only points elsewhere and makes the required reading order and source of truth explicit.

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/addicted2crypto/dcgp/claude-md
Clone the repo
git clone --depth 1 https://github.com/addicted2crypto/DCGP
Per session 161 This file is loaded in full into every session.
When invoked 161 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 $0.00161 $0.00161
Opus 5 $0.00081 $0.00081
Sonnet 5 $0.00032 $0.00032
Haiku 4.5 $0.00016 $0.00016

Measured 2d ago against content hash 77ed7819bc28, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

DCGP 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 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.

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 · 12 lines

What it actually says

DCGP-governed repository (Claude Code mount)

This file is a mount point. The lead governance rules live in:

  1. HARDRULES.md - absolute user rules, override everything do not overlook, EVER!!
  2. AGENTS.md - full DCGP operational spec (7-step loop, formula, never-list)
  3. DCGP-SPEC.md - normative protocol

Before any action, read those three in order. Editing this file does nothing; edit AGENTS.md or HARDRULES.md instead.

If the repo state disagrees with any document, scripts/verify-dcgp.sh is the tiebreaker.

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. 2d ago First seen · 12 lines · 161 tokens per session scan A 77ed7819bc28

Subscribe to this mod's changes

DCGP CLAUDE.md is an instructions file published in the GitHub repository addicted2crypto/DCGP (5 stars, last pushed 3d ago), licensed MIT. It adds 161 tokens to every session, about $0.0008 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 2026-08-31.