clawock CLAUDE.md

clawock CLAUDE.md is an instructions file for coding agents from KCNyu/clawock. It costs 867 tokens per session, scanned A, original, MIT.

Project-specific instructions for Claude Code in an investment workspace. They point the agent to identity, user preferences, memory, tools, investment procedures, and other required files.

In plain words
What is it for?
Use them to guide every session in that workspace, including investment questions, scheduled runs, tool selection, and locating canonical project information.
Why use it?
They give the coding agent the project’s operating rules and required reading order before it takes action.

Instructions file

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/kcnyu/clawock/claude-md
Clone the repo
git clone --depth 1 https://github.com/KCNyu/clawock

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 clawock CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kcnyu/clawock/claude-md.svg)](https://agentmods.dev/instructions/kcnyu/clawock/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kcnyu/clawock/claude-md"><img src="https://agentmods.dev/badge/instructions/kcnyu/clawock/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 867 This file is loaded in full into every session.
When invoked 867 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 $0.00867 $0.00867
Opus 5 $0.00434 $0.00434
Sonnet 5 $0.00173 $0.00173
Haiku 4.5 $0.00087 $0.00087

Measured 5d ago against content hash a7cdead5578d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clawock 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 5d 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 · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Entry pointer for Claude Code in kcn's investment workspace. Same workflow as AGENTS.md (openclaw entry) — content lives in the canonical files below, this is just the road map.

Identity & user

  • You're Rick (see IDENTITY.md)
  • User is kcn / Shengyu Li (see USER.md)

Required reads (every session, in order)

  1. SOUL.md — disposition / how to think
  2. USER.md — who kcn is + preferences
  3. MEMORY.md — iron data rules + known traps
  4. TOOLS.md — scripts / fallback chains / skill routing / cron map
  5. INVESTMENT_SOP.md — investment-question startup sequence
  6. portfolio.json — lazy-load when needed

What lives where

Topic File
Disposition / persona SOUL.md, IDENTITY.md
User profile / preferences USER.md
Iron rules / traps MEMORY.md
Scripts / fallback / skill routing / cron TOOLS.md
Skill bodies skills/{name}/SKILL.md
Portable workflows / market / portfolio tools installed clawock CLI; source in src/clawock/
Harness CLI / live profile clawock brief|report|intraday; package-owned lifecycle selected by CLAWOCK_PROFILE
Host / publish / CI / growth wiring ops/{host,publish,ci,growth}/
Repository automation installed clawock-* commands and named ops/* entry points
Daily deep brief output memory/{date}-pre-open.md + memory/{date}-plan.json
Daily portfolio snapshots memory/snapshots/{date}.json
Preflight context (gitignored) memory/.tmp/
Startup sequence INVESTMENT_SOP.md
Heartbeat workflow HEARTBEAT.md (heartbeat poll only)
Auto-commit rules AGENTS.md
Interactive code PR/worktree rules AGENTS.md § Interactive Codex/Claude PR workflow
Getting a merged fix onto this host (no release needed) ops/host/refresh_live.sh; rule in docs/operations/release.md § Running the latest code on this host
Pages dashboard input data-plane generation refreshed by KCNyu postflight and ops/publish/publish_dashboard.sh
Risk metrics snapshot assets/data/risk.json (built by clawock portfolio-risk, refreshed daily via brief preflight)
Decision execution marking memory/decisions.jsonl execution.status; manual override via clawock mark-followed DECISION_ID [--no]
Pages source site/index.html (dashboard) + site/briefs.md (daily briefs index)

Read the full file on GitHub · 62 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. 5d ago First seen · 62 lines · 867 tokens per session scan A a7cdead5578d

Subscribe to this mod's changes

clawock CLAUDE.md is an instructions file published in the GitHub repository KCNyu/clawock (14 stars, last pushed today), licensed MIT. It adds 867 tokens to every session, about $0.0043 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

Vibe-Research AGENTS.md

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/).

simonlin1212/Vibe-Research · 4,469 tokens

TradingAgents-astock CLAUDE.md

Claude Code instructions for simonlin1212/TradingAgents-astock, covering tradingagents-astock, 项目概述, 架构, 数据层(v0.2.5 全部直连 http,零第三方数据库依赖) and agent 角色(7 个).

simonlin1212/TradingAgents-astock · 3,359 tokens

aifi AGENTS.md

Instructions for iFurySt/aifi, covering aifi, read at the start of each task, read before finishing a code change, read when the task needs it and working rules.

iFurySt/aifi · 449 tokens

aifi CLAUDE.md

Instructions for iFurySt/aifi, a project described as: 💰 AIFi (AI Finance) is an agent-first workspace for compounding investment research and insight.

iFurySt/aifi · 15 tokens

daily-watchlist CLAUDE.md

Instructions for Benboerba620/daily-watchlist: This file is the source protocol for the Daily Watchlist workflow. Hypothesis Tracker is bundled in this repository as the thesis/evidence layer.

Benboerba620/daily-watchlist · 324 tokens

personal-finance-skill CLAUDE.md

Instructions for 6missedcalls/personal-finance-skill, covering personal finance skill — developer guide, skill documentation, project structure, stack and rules.

6missedcalls/personal-finance-skill · 984 tokens