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/backtocimacoppi/praxis/claude-mdgit clone --depth 1 https://github.com/BackToCimaCoppi/PraxisWrote 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/backtocimacoppi/praxis/claude-md)<a href="https://agentmods.dev/instructions/backtocimacoppi/praxis/claude-md"><img src="https://agentmods.dev/badge/instructions/backtocimacoppi/praxis/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 | $0.01745 | $0.01745 |
| Opus 5 | $0.00873 | $0.00873 |
| Sonnet 5 | $0.00349 | $0.00349 |
| Haiku 4.5 | $0.00175 | $0.00175 |
Grade A, and why
Praxis 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Praxis 贡献规范(AI 与人共同遵守)
本文件是向 Praxis 新增或修改 skill 的规范真值源。任何人(含用 Claude Code 操作的 AI) 往本仓库加 skill 时,必须逐条对齐以下规则,使全库格式始终统一——不靠记忆、不靠自觉。
这是 Claude Code 自动加载的项目指令。AI 在本仓工作时默认遵守本文件。
1. Skill 格式
- 目录:
skills/<kebab-名>/,主文件skills/<kebab-名>/SKILL.md。名称用小写连字符(kebab-case)。 - frontmatter(SKILL.md 开头的 YAML)必须含:
name:与目录名一致description:一句话用途 + 触发词(用户说什么词会触发本 skill)- 可选
allowed-tools:限定本 skill 能用的工具
- 只放通用引擎:任何项目特定值(目录路径、业务域、死亡线区域、金标准领域、真实审查人、
服务器/数据库信息)一律不硬编码,而是声明为「项目级补丁挂载点」,由使用者按
templates/项目级补丁模板/自行填充。 - 权限角色不得折叠成“用户”:任务发起人、业务决策负责人、环境所有者/发布授权人、候选验收人是独立角色;个人项目可以由一人兼任,团队项目可按职责分离。skill 不得因当前交互方启动任务、批准计划或触发 goal,就推定其拥有环境抢占、生产发布或最终验收权限。
- 共享环境策略只由项目补丁声明:通用 skill 不硬编码占用有效期、失效判据或抢占规则;启动任务不构成环境授权。没有释放、按规则失效或环境所有者明确授权时,优先隔离环境,否则交付可恢复阻塞。
- 跨 skill 引用用同级相对路径(如
adversarial-review/references/证据包制作规范.md),绝不写本机绝对路径。 - 附属文件放
references/(参考文档)、assets/(模板)、scripts/(脚本)子目录;脚本用环境变量 解析路径,禁止硬编码绝对路径。
2. 文档格式
-
每个 skill 必须配一篇
docs/<名>.md,文件名与 skill 同名。 -
强制四段式结构,标题原样、顺序不变:
# <skill 名> > 一句话定位 ## 这是什么 —— 干什么 + 边界(管什么 / 不管什么) ## 解决什么问题 —— 不用它会遇到什么痛点(问题空间语言) ## 为什么这么设计 —— 核心机制 + 关键取舍 ## 怎么用 —— 触发词 / 流程 / 最小示例 / 常见坑 -
简体中文,面向初次接触者,手把手但不啰嗦(建议 60–180 行)。
-
新增 skill 后,必须同步在
README.md的 Skill 总表里加一行 (名称 + 一句话 + 场景 + 跳转docs/<名>.md)。
3. 脱敏红线(开源仓硬约束,最高优先级)
- 禁止出现:个人信息、真实姓名/昵称、私有项目名、真实公司名、真实仓库/账号、
密钥/凭证(
sk-*、AKIA*、password、token 等)、本机绝对路径。 - 「为什么创建/为什么这么设计」只用问题空间语言——讲普遍痛点,不写任何个人或具体项目背景。
- 示例一律用通用虚构域(订单/商品/支付/优惠券等),不引用真实业务。
4. 新增 Skill 自检清单(提 PR 前逐条打勾)
-
目录为
skills/<kebab-名>/,含SKILL.md,frontmatter 有name+description(带触发词) -
无任何项目特定硬编码,项目特定值都走补丁挂载点
-
已区分治理角色;未把任务发起或当前交互方默认当成业务、环境、发布和验收的全部授权者
-
共享环境遵守项目占用策略;未把启动任务写成自动授权或自动抢占
-
跨 skill 引用为同级相对路径,无绝对路径
-
已写
docs/<名>.md,四段式齐全 -
README.md总表已加对应行 -
脱敏自查:对全部新增/改动文件跑下面四条,零命中
# ① 私有名词(换成你自己/你公司不希望出现的词,含私有业务域词) grep -rnE '你的昵称|你的项目代号|你的公司名|你的私有业务域词' skills/ docs/ README.md # ② 真实凭据:只拦「词后面跟着真实值」与高置信度密钥前缀 grep -rnE '(password|passwd|secret|token|api[_-]?key|private[_-]?key|密钥|凭证)[[:space:]]*[:=][[:space:]]*["'"'"']?[A-Za-z0-9_/+.-]{12,}|sk-[A-Za-z0-9_-]{12,}|AKIA[0-9A-Z]{12,}|gh[pousr]_[A-Za-z0-9]{20,}|AIza[A-Za-z0-9_-]{30,}|-----BEGIN[A-Z ]*PRIVATE KEY-----' skills/ docs/ README.md # ③ 本机绝对路径(前置边界,避免 pages/home/ 这类误报) grep -rnE '(^|[^A-Za-z0-9])/(Users|home)/[A-Za-z0-9._-]+' skills/ docs/ README.md # ④ 家目录写法的私有路径(`~/xxx/…` 会绕过第③条;只放行 skill 安装位置与虚构示例) grep -rnE '~/[A-Za-z][A-Za-z0-9._-]*/' skills/ docs/ README.md | grep -vE '~/\.(claude|agents|codex)/|~/projects/'
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.
- 5d ago First seen · 87 lines · 1,745 tokens per session scan A 0956142a0a5f
Praxis CLAUDE.md is an instructions file published in the GitHub repository BackToCimaCoppi/Praxis (6 stars, last pushed 11d ago), licensed Apache-2.0. It adds 1,745 tokens to every session, about $0.0087 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
ratel AGENTS.md
AGENTS.md instructions for ratel-ai/ratel, covering agents.md — working in the ratel repo, build & test, rust, ts and python (from src/sdk/python/; needs uv).
orchestkit CLAUDE.md
Claude Code instructions for yonatangross/orchestkit, covering claude.md, language, tone, visuals and project overview.
recursive-decomposition-skill AGENTS.md
Instructions for massimodeluisa/recursive-decomposition-skill, covering agents: recursive-decomposition skill, read these first (mandatory), language policy, non-negotiables and commands.
Assumptions AGENTS.md
Instructions for Teycir/Assumptions, covering agent instructions for this repository and assumptions skill.
ai-job-finder CLAUDE.md
Instructions for chrisdothtml/ai-job-finder: This repo uses Typescript with node.js, with Yarn as the dependency manager. You can use ./bin/tsn as a drop-in replacement for the node binary. I highly prefer to avoid adding additional third-party dependencies to my project, unless it abstracts very complex…
agent-teacher AGENTS.md
AGENTS.md instructions for JackyYang258/agent-teacher, covering agentteacher agent guide, project, repository map, commands and bilingual policy.