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.
npx agentmods add instructions/monarchjuno/tradingcodex/agents-mdgit clone --depth 1 https://github.com/monarchjuno/tradingcodexWhat 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 | $0.02165 | $0.02165 |
| Opus 5 | $0.01082 | $0.01082 |
| Sonnet 5 | $0.00433 | $0.00433 |
| Haiku 4.5 | $0.00216 | $0.00216 |
Grade A, and why
tradingcodex 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 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.
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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TradingCodex Repository Guide
Read Order And Documentation Ownership
Read in this order:
- This file for repository-wide non-negotiable rules and validation routing.
- Architecture for the codebase map, ownership, and runtime boundaries.
- Product documentation for durable behavior and rationale.
- User guide only when setup or an everyday user journey changes.
Keep each fact in one owning layer and link to it elsewhere:
| Layer | Owns |
|---|---|
docs/ |
Durable product behavior, architecture, safety, workflow, and release intent. |
guidebook/ |
Concise, task-first user instructions. |
README.md / installation.md |
Product entrypoint and installation path. |
AGENTS.md |
Repository-wide development constraints. |
Update only the owning layer unless another audience's route actually changed.
Do not mirror a rule across several documents merely to keep them textually
similar. When layers disagree, correct the owning docs/ page first.
Product Direction
TradingCodex is a thin, local-first investment layer on top of native Codex. Codex owns reasoning, research strategy, tool selection, delegation, and use of the user's available skills, plugins, apps, and MCP servers. TradingCodex owns durable investment records and deterministic boundaries for provenance, policy, approval, execution, secrets, and audit.
Do not replace native Codex capabilities with a parallel router, workflow engine, capability registry, permission system, tool-discovery protocol, agent scheduler, or provider platform. Add TradingCodex machinery only when a durable cross-session invariant or sensitive final effect cannot be handled safely by native Codex, a canonical skill bundle with a concise entrypoint, or an existing application service.
Put behavior at the first layer that can own it:
- Native Codex and user-provided capabilities.
- One canonical skill bundle with a concise
SKILL.mdentrypoint for reusable agent guidance. - A prompt for stable role identity or a safety boundary.
- An application service for durable records or deterministic enforcement.
- A hook only when enforcement must surround a native tool call.
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.
- 2d ago First seen · 198 lines · 2,165 tokens per session scan A 79e16acf331a
tradingcodex AGENTS.md is an instructions file published in the GitHub repository monarchjuno/tradingcodex (364 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,165 tokens to every session, about $0.0108 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.
Other instructions, from other repositories
Vibe-Research AGENTS.md
Instructions for simonlin1212/Vibe-Research, covering vibe-research-agent 金融研究宪法, 0. 三条不可越线, 1. 数据纪律(五问 gate:给出任何数字或结论前逐条自问), 2. 研究哲学(评估框架,不是预测工具) and 3. 估值口径(你只选输入、解释输出;计算交给 calc/).
cctop AGENTS.md
Instructions for st0012/cctop, covering agents.md - development guide for cctop, scope and sources, required development rules, driver workflow and github and pr rules.
toh-framework CLAUDE.md
Instructions for wasintoh/toh-framework, covering claude.md — toh framework (repo development guide), what this is, everyday commands, verification protocol and single source, transformed per ide.
clawock AGENTS.md
Instructions for KCNyu/clawock, covering agents.md - your workspace, every session, kcn 偏好, git hook (one-time setup per clone) and git auto-commit rules.
examples CLAUDE.md
Claude Code instructions for rossoctl/examples, covering claude.md - agent examples, repository structure, key commands, code style and dco sign-off (mandatory).
agent-rules child-process.instructions.md
Instructions for lirantal/agent-rules, covering system processes secure coding guidelines, your mission and spawning system processes.