Borrowing it
Nothing to install: this file belongs to BigKunLun/AI-Coding-Insights. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/BigKunLun/AI-Coding-Insights/main/CLAUDE.mdgit clone --depth 1 https://github.com/BigKunLun/AI-Coding-InsightsWrote 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.
[](https://agentmods.dev/instructions/bigkunlun/ai-coding-insights/claude-md)<a href="https://agentmods.dev/instructions/bigkunlun/ai-coding-insights/claude-md"><img src="https://agentmods.dev/badge/instructions/bigkunlun/ai-coding-insights/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.04427 | $0.04427 |
| Opus 5 | $0.02214 | $0.02214 |
| Sonnet 5 | $0.00885 | $0.00885 |
| Haiku 4.5 | $0.00443 | $0.00443 |
Grade A, and why
AI-Coding-Insights 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 6d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
项目定位
评估一个人对 AI 编码工具的使用情况:分析其本机的 Claude Code 会话记录,做深度分析,给出画像与改进建议。形态是 Claude Code plugin,由用户本人手动触发,产出本机报告。机器只给分析与证据,结论与奖惩判决在人。
常用命令
uv run pytest # 全量测试
uv run pytest tests/test_window.py # 单文件
uv run pytest tests/test_window.py::test_xxx # 单用例
# 规则层手动调试(正常由 skill 编排调用)
uv run python -m ai_coding_insights scan --plugin-root . --emit-batches ~/.ai-coding-insights/run
# 指定来源(不传则跟触发环境走)
uv run python -m ai_coding_insights scan --source codex --emit-batches ~/.ai-coding-insights/run
# 安装器预演:看 playbook 会落到哪、有没有走降级版(不写盘)
uv run python -m ai_coding_insights install --print
零运行时依赖(纯 stdlib),dev 仅 pytest。
规则层共 8 个子命令,正常由 skill 编排调用,单独调试时也可直接跑(点到存在即可,参数以代码为准)。这份清单有测试守着(tests/test_skill_contract.py):子命令名与条数必须与 cli.py 实际注册面一致,加了子命令不补这里即测试红。
scan—— 扫描 / 窗口决策 / 分批 / 硬指标;--emit-batches是编排主路径,四种输出形态互斥(--emit-batches/--profile-input/--json/ 默认渲染 HTML)。init—— 交互配置向导,从本机会话来源勾选团队归属。verify-obs—— 校验 LLM 观测(obs)对批次的覆盖与 posture 计数完整性。render-profile—— 渲染最终画像 HTML 报告。auto-scan——SessionEndhook 后台自动评估(接线在hooks/hooks.json;自带 lock 防重入 + 滚动日志,失败对用户静默)。reset—— 清空本机可再生产物(snapshots//reports//run//auto-scan.log)解除 30 天增量窗口闸门,并把今日写进.auto-scan.lock(而非删它),压住SessionEnd的 auto-scan 当天抢先写新快照重新武装闸门——这是「reset 后重跑仍 too_soon」的根因修复。按白名单删、--dry-run只预览,永不碰config.toml与会话原文。slash 入口commands/reset.md。install—— 统一安装器:把单一真相源 playbook(skills/ai-coding-insights/SKILL.md)渲染并落到当前 harness 该放的位置。「装哪一家」与取数一样跟触发环境走(--source可覆盖);--print只预演落点不写盘,目标已存在须--force才覆盖(用户可能改过自己的 playbook)。三个薄适配器在installers.py,各配一条契约测试。无子代理能力的 harness 会装降级编排版,且降级状态写进报告 caveat——静默劣化是本项目定义的最危险故障。calibrate—— 手动调试命令:给出各指标分布与当前阈值的分位定位,不进 SKILL.md 编排、不产 HTML。两种取数来源:默认读snapshots/里已脱敏的历史标量;--replay则把本机会话按等长窗口切片重放成伪快照(--replay-window默认对齐WINDOW_FLOOR_DAYS,--replay-step可滑动)。回放存在的理由:窗口闸门是「不足 30 天即 too_soon」,快照最快 30 天落一个,攒 20 个要 1.6 年——靠等快照校准阈值走不通,而档位闸门用的全是规则层硬指标,可直接从既有会话按同口径重算。切片长度必须与评估窗口同口径,改小即跨口径(阈值是按「一个 30 天窗口内的量级」定的)。回放不跑 git log、不跑 LLM,git 三键与姿态四档整键不放进伪快照(未测量 ≠ 0)。只给本机单人分布,不是人群分位;样本不足时逐层挂 caveat,且 n < 5 时压住「过门/未过门」的定性读法,只给数字。
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.
- 6d ago First seen · 81 lines · 4,427 tokens per session scan A 5b680081a982
AI-Coding-Insights CLAUDE.md is an instructions file published in the GitHub repository BigKunLun/AI-Coding-Insights (5 stars, last pushed 18d ago), licensed MIT. It adds 4,427 tokens to every session, about $0.0221 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.