agentmods.dev

cc-statistics CLAUDE.md

Project guidance for cc-statistics, a Python command-line tool that measures Claude Code session activity from JSONL files, a line-based JSON data format. It explains setup, usage, architecture, metrics, and code-review rules.

In plain words
What is it for?
Listing or analyzing projects and recent sessions, counting instructions and tool calls, measuring time and tokens, estimating edited code lines, and reviewing changes for security and performance.
Why use it?
It helps agents understand where session data comes from and how the tool calculates and presents its results safely.

Instructions file

114 26d ago A scan 912 tokens original MIT
View the source file androidZzT/cc-statistics
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/androidzzt/cc-statistics/claude-md
Clone the repo
git clone --depth 1 https://github.com/androidZzT/cc-statistics
Per session 912 This file is loaded in full into every session.
When invoked 912 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 $0.00912 $0.00912
Opus 5 $0.00456 $0.00456
Sonnet 5 $0.00182 $0.00182
Haiku 4.5 $0.00091 $0.00091

Measured 2d ago against content hash dda94479cb4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cc-statistics 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 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.

CLAUDE.md · 68 lines

What it actually says

CLAUDE.md

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

Project

cc-statistics — CLI 工具，用于统计 Claude Code 会话的 AI Coding 工程指标。

数据源：~/.claude/projects/ 下的 JSONL 会话文件。

Setup

python3 -m venv .venv
source .venv/bin/activate
pip install -e .

Usage

cc-stats --list              # 列出所有项目
cc-stats                     # 分析当前目录项目
cc-stats <project-keyword>   # 按关键词匹配项目
cc-stats <path/to/file.jsonl> # 分析指定 JSONL
cc-stats --all               # 分析所有项目
cc-stats --last N            # 只看最近 N 个会话

Architecture

  • cc_stats/parser.py — 解析 JSONL 为 Session/Message 数据结构
  • cc_stats/analyzer.py — 从 Session 计算 5 项工程指标（指令数、工具调用、时长、代码行数、token）
  • cc_stats/formatter.py — 将统计结果格式化为终端表格输出
  • cc_stats/cli.py — argparse CLI 入口，负责文件发现和参数处理

Key conventions

  • 纯 Python stdlib，无第三方依赖
  • 用户消息判定：type == "user" 且 is_tool_result == False 且 is_meta == False
  • 活跃时间：消息间隔 ≤ 5 分钟视为活跃
  • 代码行数来自 Edit/Write 工具调用的 input 参数

Code Review 规范

所有代码变更（包括社区 PR）在合并前必须通过以下安全和性能检查。

安全检查清单

  • Shell/Script 注入防护：所有拼接到 AppleScript、shell command、osascript 的字符串必须转义（反斜杠、双引号等特殊字符）。禁止直接字符串插值到脚本模板中
  • 外部输入不可信：文件名、项目名、路径等来自用户或文件系统的值，不可直接拼入命令或脚本。必须经过清洗或转义
  • JSONL 解析防御：解析外部 JSONL 文件时，对缺失字段、类型不匹配、格式异常做防御性处理，不可因单条脏数据导致整体崩溃
  • 无硬编码敏感信息：代码中不包含 API key、token、密码等敏感信息

性能检查清单

  • 禁止循环中同步子进程：不可在 for 循环内调用 Process()/subprocess 等同步外部命令。如需批量执行，使用批处理或异步方式
  • 时间复杂度评估：对遍历全量 sessions/messages 的逻辑，评估时间复杂度。避免 O(N²) 或更高复杂度的嵌套循环；优先使用单次遍历 + 分桶/索引
  • IO 密集操作需异步或缓存：磁盘读取、文件遍历等 IO 操作应考虑缓存策略，避免重复读取。大量文件操作应在后台线程执行
  • 避免不必要的全量重算：筛选条件变更时，如果数据源未变，应复用缓存而非重新加载

PR Review 流程

  1. 自动检查：PR 提交后，CI 必须通过编译检查
  2. 安全审查：涉及字符串拼接、外部输入处理、命令执行的变更，必须逐行确认转义和清洗
  3. 性能审查：涉及数据遍历、子进程调用、IO 操作的变更，必须评估大数据量下的表现
  4. 社区 PR 额外要求：社区贡献者的 PR 需项目维护者 approve 后方可合并，重点关注安全和性能两项
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. 2d ago First seen · 68 lines · 912 tokens per session scan A dda94479cb4d

Subscribe to this mod's changes

cc-statistics CLAUDE.md is an instructions file published in the GitHub repository androidZzT/cc-statistics (114 stars, last pushed 26d ago), licensed MIT. It adds 912 tokens to every session, about $0.0046 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.

Analytics and metricsLanguagesPythonai-codingclaude-codeclicost-estimationdeveloper-toolsgemini-cli
Related

Other instructions, from other repositories

parallel-code CLAUDE.md

Instructions for johannesjo/parallel-code, covering parallel code, stack, commands, project structure and conventions.

johannesjo/parallel-code · 257 tokens

map-framework CLAUDE.md

Instructions for azalio/map-framework, covering map framework (mapify-cli) — agent instructions, what this repo is, critical invariant: template single-source render, skill catalog invariant and how to work in this repo.

azalio/map-framework · 1,601 tokens

PokeTokenBar CLAUDE.md

Instructions for chattymin/PokeTokenBar, covering poketokenbar — claude 프로젝트 지침, 참조 문서 (필요할 때 읽는다), 기여 언어 규약 (오픈소스 대비 — english first), 릴리스 (자연어 트리거) and 확장 규약 (새 프로바이더/툴 추가 시).

chattymin/PokeTokenBar · 1,918 tokens

intuitive-flow AGENTS.md

Instructions for MiaoDX/intuitive-flow, covering codex guide, environment, delegation and verification, development and testing and preferred skills and workflow routing.

MiaoDX/intuitive-flow · 1,431 tokens

SubFrame AGENTS.md

Instructions for Codename-11/SubFrame, covering subframe - subframe project, core working principle, relationship to native ai tools, session start and concurrent work & worktrees.

Codename-11/SubFrame · 3,973 tokens

SubFrame CLAUDE.md

Instructions for Codename-11/SubFrame, covering subframe, core rule, architecture, tech stack and key modules.

Codename-11/SubFrame · 5,031 tokens