agentforge-graph CLAUDE.md

A Claude Code instruction file that points to AGENTS.md, the project's main guide for working conventions. It also leaves a place for Claude-specific instructions.

In plain words
What is it for?
Use it to connect Claude Code with a project's shared AgentForge instructions and add rules that apply only to Claude Code.
Why use it?
It keeps Claude Code's automatic instruction lookup working while maintaining one canonical set of project rules.

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/scaffoldic/agentforge-graph/claude-md
Clone the repo
git clone --depth 1 https://github.com/Scaffoldic/agentforge-graph
Per session 133 This file is loaded in full into every session.
When invoked 133 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.00133 $0.00133
Opus 5 $0.00067 $0.00067
Sonnet 5 $0.00027 $0.00027
Haiku 4.5 $0.00013 $0.00013

Measured 2d ago against content hash 193b38f2158e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

agentforge-graph CLAUDE.md scanned grade C with 1 finding 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- Claude Code-specific instructions go here. This section survives `agentforge upgrade`. -->
CLAUDE.md · 15 lines

What it actually says

See AGENTS.md for AgentForge conventions. Claude Code reads both files; AGENTS.md is the canonical source.

This file exists so Claude Code's native CLAUDE.md discovery keeps working. Put Claude-Code-specific instructions in the custom section below.

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 · 15 lines · 133 tokens per session scan C 193b38f2158e

Subscribe to this mod's changes

agentforge-graph CLAUDE.md is an instructions file published in the GitHub repository Scaffoldic/agentforge-graph (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 133 tokens to every session, about $0.0007 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.