offercatcher: Instructions file for Claude Code

CLAUDE.md

offercatcher CLAUDE.md is an instructions file for Claude Code from NissonCX/offercatcher. It costs 687 tokens per session, scanned A, original, MIT.

Project instructions for OfferCatcher, a tool that scans Apple Mail for recruiting messages, uses OpenClaw to interpret them, and creates Apple Reminders. OpenClaw is the language-model system used to parse the messages.

In plain words
What is it for?
They are for scanning recruiting emails, previewing or applying parsed reminder events, recording events manually, and running the project's tests.
Why use it?
They explain how the email-to-reminder workflow is structured and provide the expected event format, reducing mistakes when scanning or applying results.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; built for openclaw.

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

Reuse

Borrowing it

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

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 offercatcher CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nissoncx/offercatcher/claude-md/github.svg)](https://agentmods.dev/instructions/nissoncx/offercatcher/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nissoncx/offercatcher/claude-md"><img src="https://agentmods.dev/badge/instructions/nissoncx/offercatcher/claude-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.

agentmods 80×15 button for offercatcher CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nissoncx/offercatcher/claude-md"><img src="https://agentmods.dev/badge/instructions/nissoncx/offercatcher/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 687 This file is loaded in full into every session.
When invoked 687 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 $0.00687 $0.00687
Opus 5.5 $0.00275 $0.00275
Sonnet 5.5 $0.00137 $0.00137
Haiku 4.5 $0.00069 $0.00069

Measured 2mo ago against content hash c05a2e3e82c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

offercatcher 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 2mo 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 · 90 lines

What it actually says

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

项目概述

OfferCatcher 是一个招聘邮件提醒同步工具,配合 OpenClaw 使用。通过 Apple Mail 扫描邮件,OpenClaw LLM 解析内容,Apple Reminders 创建提醒。

架构

┌─────────────┐     ┌─────────────┐     ┌─────────────┐
│  scan-only  │ --> │ OpenClaw    │ --> │ apply-events│
│  获取邮件   │     │ LLM 解析    │     │ 创建提醒    │
└─────────────┘     └─────────────┘     └─────────────┘

不使用正则匹配:邮件解析由 OpenClaw LLM 完成,能适应各种格式的邮件。

常用命令

扫描邮件

python3 scripts/recruiting_sync.py --scan-only

返回原始邮件 JSON,供 OpenClaw LLM 解析。

应用 LLM 解析结果

python3 scripts/recruiting_sync.py --apply-events /tmp/events.json --dry-run
python3 scripts/recruiting_sync.py --apply-events /tmp/events.json

手工记录事件

python3 scripts/manual_event.py --title "重要事件" --due "2026-04-01 10:00" --notes "入口:https://example.com"

运行测试

python3 -m unittest discover tests/ -v

事件 JSON 格式

apply-events 接受的 JSON 格式:

{
  "events": [
    {
      "id": "唯一标识",
      "company": "公司名称",
      "event_type": "interview | written_exam | assessment | authorization | deadline",
      "title": "提醒标题",
      "timing": {"start": "YYYY-MM-DD HH:MM", "end": "..."} 或 {"deadline": "..."},
      "role": "岗位名称",
      "link": "入口链接",
      "message_id": "原始邮件ID",
      "subject": "邮件主题",
      "sender": "发件人"
    }
  ]
}

核心文件

文件 作用
scripts/recruiting_sync.py 主脚本:scan-only / apply-events
scripts/apple_reminders_bridge.py Apple Reminders 桥接
scripts/manual_event.py 手工记录事件
scripts/list_mail_sources.py 列出 Apple Mail 账户

配置文件

~/.openclaw/offercatcher.yaml:

mail_account: 谷歌    # Apple Mail 账号名
days: 2               # 扫描天数
max_results: 60       # 最大邮件数

编码规范

  • Python 3.11+,dataclass 定义数据结构
  • 中文注释和输出
  • 遵循 PEP 8
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. 2mo ago First seen · 90 lines · 687 tokens per session scan A c05a2e3e82c2

Subscribe to this mod's changes

offercatcher CLAUDE.md is an instructions file published in the GitHub repository NissonCX/offercatcher (22 stars, last pushed 6mo ago), licensed MIT. It adds 687 tokens to every session, about $0.0027 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.

Related

offercatcher CLAUDE.md compared with instructions from other repositories

offercatcher CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
offercatcher CLAUDE.mdNissonCX/offercatcherInstructions file226mo agoMITA687Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode