agentmods.dev

EVClaw AGENTS.md

Repository instructions for EVClaw, an open-source, network-connected trading system. They describe its main programs, operating rules, tool expectations, and scheduled safety checks.

In plain words
What is it for?
Working on EVClaw's trading, monitoring, reconciliation, health, and scheduled cron workflows.
Why use it?
They give coding agents a shared map of the system and prevent them from assuming unavailable services or skipping required operations.

Instructions file for CodexOpenCode

40 2mo ago A scan 1,755 tokens original MIT
View the source file Degenapetrader/EVClaw
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/degenapetrader/evclaw/agents-md
Clone the repo
git clone --depth 1 https://github.com/Degenapetrader/EVClaw

Made for: Codex, OpenCode.

Per session 1,755 This file is loaded in full into every session.
When invoked 1,755 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 $0.01755 $0.01755
Opus 5 $0.00877 $0.00877
Sonnet 5 $0.00351 $0.00351
Haiku 4.5 $0.00176 $0.00176

Measured 3d ago against content hash 195d1fa31a77, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

AGENTS.md · 160 lines

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.sh
    • openclaw 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.md and MANUAL_COMMANDS together.
  • For scheduled cron turns, follow CRON_CONTEXT plus Tool.md CRON_SAFE_TOOLS block 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.py every cycle.
  • Retention is fixed in code to keep last 50 files 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.

Read the full file on GitHub · 160 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. 3d ago First seen · 160 lines · 1,755 tokens per session scan A 195d1fa31a77

Subscribe to this mod's changes

EVClaw AGENTS.md is an instructions file published in the GitHub repository Degenapetrader/EVClaw (40 stars, last pushed 2mo ago), licensed MIT. It adds 1,755 tokens to every session, about $0.0088 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.

Finance and fintech
Related

Other instructions, from other repositories

cryptoexchange-net

Use CryptoExchange.Net abstractions when generating C#/.NET code that needs to work across MULTIPLE cryptocurrency exchanges (Binance + Bybit + OKX + Kraken + Coinbase + ...) — for arbitrage, best-execution routing, multi-exchange portfolio dashboards, exchange-agnostic trading bots, or comparison tools. Triggers on…

JKorf/CryptoExchange.Net · 2,291 tokens

OpenCandle AGENTS.md

Instructions for Kahtaf/OpenCandle, covering opencandle, commands, where to look, code style and conventions.

Kahtaf/OpenCandle · 1,628 tokens

claude-finance-kit CLAUDE.md

Instructions for hongbietcode/claude-finance-kit, covering claude finance kit assistant, scope, operating principles, skill (single entry point) and references (load when needed).

hongbietcode/claude-finance-kit · 2,209 tokens

creditkarma-mcp CLAUDE.md

Claude Code instructions for chrischall/creditkarma-mcp, covering creditkarma-mcp, commands, tool naming, architecture and auth resolution (pattern a template).

chrischall/creditkarma-mcp · 4,135 tokens

bullet-bots AGENTS.md

Instructions for bulletxyz/bullet-bots, covering bullet-bots, build & test, run the faucet curl printed by keygen, then, or (base58 from phantom/delegation export, or hex) and architecture — the harness, feeds, and actors.

bulletxyz/bullet-bots · 3,972 tokens

romaco-mcp AGENTS.md

AGENTS.md instructions for romaco-labs/romaco-mcp, covering purpose, read first, product boundaries, architecture invariants and development method.

romaco-labs/romaco-mcp · 679 tokens