Borrowing it
Nothing to install: this file belongs to Degenapetrader/EVClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Degenapetrader/EVClaw/main/AGENTS.mdgit clone --depth 1 https://github.com/Degenapetrader/EVClawWrote 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/degenapetrader/evclaw/agents-md)<a href="https://agentmods.dev/instructions/degenapetrader/evclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/degenapetrader/evclaw/agents-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.
<a href="https://agentmods.dev/instructions/degenapetrader/evclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/degenapetrader/evclaw/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01755 | $0.01755 |
| Opus 5.5 | $0.00702 | $0.00702 |
| Sonnet 5.5 | $0.00351 | $0.00351 |
| Haiku 4.5 | $0.00176 | $0.00176 |
Grade A, and why
EVClaw AGENTS.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 1mo 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EVClaw AGENTS
Purpose: compact runtime contract for AI agents/operators working in this repo.
Mission
- Run EVClaw as an OSS, network-first AGI trading system.
- Keep behavior deterministic where possible (ops/health/reconcile).
- Keep LLM decisions constrained to entry/exit decision tasks.
- Never assume private VPS-local files/services beyond this repo defaults.
System map
cycle_trigger.py: ingest cycle + build context.live_agent.py/live_agent_process.py: entry pipeline + execution path.llm_exit_decider.py/hip3_exit_decider.py: exit decisions.hourly_ops.py: deterministic safety/reconcile/health runner.run_fill_reconciler.py: fill tracking + reconciliation.live_monitor.py: equity snapshots used by SR/equity safety checks.
Cron install requirement (critical)
- EVClaw deterministic safety/reporting depends on OpenClaw cron jobs being installed and active.
- After fresh setup or any repo update, run:
./scripts/install_openclaw_crons.shopenclaw cron list --json
- Expected jobs:
EVClaw AGI Trader Hourly (deterministic)EVClaw AGI Trader Hourly Report (system-event)
- If missing, scheduled safety checks, repo update checks, and update notifications will not run.
Tool map contract
- Canonical tool routing and usage are defined in
Tool.md. - For manual/advisor turns, follow
Tool.mdandMANUAL_COMMANDStogether. - For scheduled cron turns, follow
CRON_CONTEXTplusTool.mdCRON_SAFE_TOOLSblock only. - Do not invent command syntax; use the exact command forms documented in
Tool.md.
Runtime artifacts:
- DB:
${EVCLAW_DB_PATH:-./ai_trader.db} - Ops JSON:
${EVCLAW_RUNTIME_DIR:-./state}/hourly_ops_report.json - Ops summary:
${EVCLAW_RUNTIME_DIR:-./state}/hourly_ops_summary.txt - Cycle/context/candidate artifacts are auto-pruned by
cycle_trigger.pyevery cycle. - Retention is fixed in code to keep last
50files per class (safety floor:20).
AGI flow contract (high level)
- Entry: cycle trigger -> context -> entry gate -> executor.
- Exit: producers (plan-only) -> exit decider -> executor close.
- Producers never place orders directly.
- Executor stays limit/chase-limit oriented.
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.
- 1mo ago First seen · 160 lines · 1,755 tokens per session scan A 195d1fa31a77
EVClaw AGENTS.md is an instructions file published in the GitHub repository Degenapetrader/EVClaw (40 stars, last pushed 4mo ago), licensed MIT. It adds 1,755 tokens to every session, about $0.0070 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.