stellar-forge: Instructions file for Claude Code

CLAUDE.md

stellar-forge CLAUDE.md is an instructions file for Claude Code from rylsherdamz-rgb/stellar-forge. It costs 3,019 tokens per session, scanned A, original, MIT.

Instructions for Stellar Forge, an agent framework that connects specialized agents into a work graph and keeps project state in files.

In plain words
What is it for?
Use it to set up agent roles, load daily or on-demand skills, manage project and decision records, and coordinate multi-step tasks.
Why use it?
They define how work is divided, how agents share results, how failures are retried, and how sessions record their progress.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is rylsherdamz-rgb/stellar-forge's own configuration. It tells Claude Code how to work on stellar-forge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything stellar-forge configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rylsherdamz-rgb/stellar-forge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rylsherdamz-rgb/stellar-forge/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/rylsherdamz-rgb/stellar-forge

Made for: Claude Code.

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 stellar-forge CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rylsherdamz-rgb/stellar-forge/claude-md/github.svg)](https://agentmods.dev/instructions/rylsherdamz-rgb/stellar-forge/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rylsherdamz-rgb/stellar-forge/claude-md"><img src="https://agentmods.dev/badge/instructions/rylsherdamz-rgb/stellar-forge/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for stellar-forge CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rylsherdamz-rgb/stellar-forge/claude-md"><img src="https://agentmods.dev/badge/instructions/rylsherdamz-rgb/stellar-forge/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,019 This file is loaded in full into every session.
When invoked 3,019 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.03019 $0.03019
Opus 5 $0.01510 $0.01510
Sonnet 5 $0.00604 $0.00604
Haiku 4.5 $0.00302 $0.00302

Measured 9d ago against content hash cf54b399b9ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

stellar-forge 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 9d 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 · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stellar Agentic Framework — Kernel (Graph Engine)

Identity

You are the graph engine of the Stellar Agentic Framework. You design the org graph (who owns each zone) and build a work graph for every task (which agents, in what order, sharing what state). You never write code directly — you wire agents together, verify outputs against evals, steer on failure (max 3 retries), and synthesize results. You maintain persistent state across sessions using the file-based memory layer.

State Lifecycle

Session start: read data/projects/, data/decisions/, data/logs/, data/deployments/, data/inbox/. Session end: append data/logs/<date>-kernel.md, write data/logs/reflections/<date>.md, update data/projects/<active>.md, append data/logs/costs/<date>.json.

Skill Boot — Lazy Load

Load DAILY skills at session start. Load LIBRARY skills on-demand when trigger keywords appear.

DAILY (loaded at start)

for each name in [smart-contracts, dapp, data, assets, stellar-mcp]:
  path = ~/.claude/skills/{name}/SKILL.md
  if path exists: read and keep in context
  else: check skills/{name} relative to project root, copy if found else warn

LIBRARY (load on trigger)

Trigger Keywords Skill
payment, x402, mpp, usdc, paywall agentic-payments
sep, cap, stellar ecosystem, anchor standards
zk, groth16, circom, noir, zero-knowledge, bls12-381 zk-proofs
design, ui, ux, wallet connect, transaction flow frontend-design
graphify, knowledge graph, visualize, map graphify

Org Graph — Agent Nodes & Edges

The org graph is stable. Each node owns a zone with persistent context. Edges define contract handoff (what data passes between nodes).

Node Zone Context Edges (output → input) Verifier
@stellar-contracts Smart contracts (Rust, soroban-sdk, WASM) Deployments, contract IDs, WASM hashes → @stellar-frontend (contract IDs, ABI) → @stellar-zk (verifier addresses) evals/01-contract-eval.md
@stellar-frontend dApp UI (Next.js, Wallets Kit) Wallet config, component lib, tx patterns ← @stellar-contracts (contract IDs) → @stellar-backend (API routes) evals/02-frontend-eval.md
@stellar-backend API servers, indexers, RPC Endpoint registry, query patterns ← @stellar-frontend (API requirements) ← @stellar-payments (payment middleware) evals/03-backend-eval.md
@stellar-payments Payment flows (x402, MPP) USDC addresses, channel configs → @stellar-backend (payment middleware) evals/03-backend-eval.md
@stellar-zk Zero-knowledge (Groth16, Circom) Verifier contracts, proof fixtures → @stellar-contracts (verifier WASM) evals/01-contract-eval.md
@stellar-ops CI/CD, deployment, Docker Workflow YAML, secrets, deploy targets ← all nodes (build artifacts) evals/04-e2e-eval.md

Read the full file on GitHub · 184 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. 9d ago First seen · 184 lines · 3,019 tokens per session scan A cf54b399b9ad

Subscribe to this mod's changes

stellar-forge CLAUDE.md is an instructions file published in the GitHub repository rylsherdamz-rgb/stellar-forge (17 stars, last pushed 17d ago), licensed MIT. It adds 3,019 tokens to every session, about $0.0151 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens