scorched: Instructions file for Claude Code

CLAUDE.md

scorched CLAUDE.md is an instructions file for Claude Code from willcassell/scorched. It costs 11,985 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions documenting a retired trading system, including its former local, Docker and rebuild procedures. The system is shut down, its scheduled jobs are disabled and its dashboard is offline.

In plain words
What is it for?
Use it as historical reference when reviewing the retired Scorched tradebot, its archived data or its shutdown handover.
Why use it?
It prevents readers from treating old operating instructions as current and records the system's final status and handover information.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: positional $N argument; mentions Claude Code.

This is willcassell/scorched's own configuration. It tells Claude Code how to work on scorched 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 scorched configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/ubuntu/tradebot-archive/.

Reuse

Borrowing it

Nothing to install: this file belongs to willcassell/scorched. 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/willcassell/scorched/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/willcassell/scorched

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 scorched CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/willcassell/scorched/claude-md.svg)](https://agentmods.dev/instructions/willcassell/scorched/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/willcassell/scorched/claude-md"><img src="https://agentmods.dev/badge/instructions/willcassell/scorched/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 11,985 This file is loaded in full into every session.
When invoked 11,985 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 $0.11985 $0.11985
Opus 5 $0.05993 $0.05993
Sonnet 5 $0.02397 $0.02397
Haiku 4.5 $0.01199 $0.01199

Measured 7d ago against content hash 4990c1d164e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

scorched 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 7d 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 · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scorched — Claude Code Context

⛔ RETIRED — SHUT DOWN 2026-08-31

This system is not running. All 9 tradebot cron jobs are disabled, the Docker stack is down, and the dashboard is offline. Experiment C was retired ~8 weeks early by owner decision after evaluate_experiment.py returned RETIRE on both kill criteria.

Final result: +1.95% (Alpaca, broker of record) over six months, against SPY +10.75% and SPMO +22.16%. 50.8% win rate, profit factor 0.887. Trade-attributable P&L was ~flat (+$5.68); the headline +2% is mostly a 2026-04-18 reconciliation correction, not trading skill.

Two positions remain open and UNMONITORED in the Alpaca paper account: MA (24) and PFE (500). Paper money, no financial risk, but their trailing stops will not fire.

  • Full record: SHUTDOWN.md (also in .handovers/2026-08-31-shutdown.md, local-only)
  • Data archive: /home/ubuntu/tradebot-archive/ (pg_dump + CSVs + logs, outside git)
  • Crontab backup: /home/ubuntu/crontab.backup.2026-08-31-shutdown

Everything below describes the system as it was when running, and is retained as reference. Restart instructions are in the handover — re-run /broker/sync and reset the experiment block in strategy.json before trusting anything.

Commands

# Run locally (outside Docker, needs .env with DATABASE_URL)
uvicorn scorched.main:app --reload --port 8000

# Docker (preferred)
docker compose up -d --build
docker compose logs tradebot -f

# Rebuild after code changes (keeps postgres data)
docker compose up -d --build tradebot

# Alembic migrations
alembic upgrade head
alembic revision --autogenerate -m "description"

# Deploy to VM (never overwrites .env on VM)
rsync -av -e "ssh -i /path/to/ssh-key.key" \
  --exclude='.venv' --exclude='.git' --exclude='__pycache__' \
  --exclude='*.pyc' --exclude='.env' \
  /path/to/scorched/ ubuntu@YOUR_VM_IP:~/scorched/

# SSH to VM
ssh -i /path/to/ssh-key.key ubuntu@YOUR_VM_IP

# Edit crontab on VM
crontab -e

Read the full file on GitHub · 327 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. 7d ago First seen · 327 lines · 11,985 tokens per session scan A 4990c1d164e1

Subscribe to this mod's changes

scorched CLAUDE.md is an instructions file published in the GitHub repository willcassell/scorched (0 stars, last pushed 8d ago), licensed MIT. It adds 11,985 tokens to every session, about $0.0599 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.

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens