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 skills add BackToCimaCoppi/Praxis --skill plan-goalgit 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/skills/backtocimacoppi/praxis/plan-goal)<a href="https://agentmods.dev/skills/backtocimacoppi/praxis/plan-goal"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/plan-goal/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.
<a href="https://agentmods.dev/skills/backtocimacoppi/praxis/plan-goal"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/plan-goal.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00149 | $0.03928 |
| Opus 5.5 | $0.00060 | $0.01571 |
| Sonnet 5.5 | $0.00030 | $0.00786 |
| Haiku 4.5 | $0.00015 | $0.00393 |
Grade A, and why
plan-goal 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 29d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plan-goal：轻量任务流程
一句话：把「调查 → 设计 → 测试设计 → 章程 → goal 执行 → 验收」整条研发流水线压进一份计划文件，保留计划批准与候选验收两个治理检查点；两者可由一人兼任，也可按项目职责分离。
设计 DNA：砍过程、不砍验收。保留防「不可逆风险 / 真值分叉 / 工具机制事实」的规则；废弃「跨会话交接 / 脚本可解析 / 弱模型防呆」类脚手架（SD/TOPIC/哈希对账、总控目录、六要素表格、多套报告模板——它们防的失败模式在单文件单会话形态下不存在）。内核只有三问：选了什么 / 为什么 / 怎么验。
0. 定位与分档
| 档位 | 判据 | 模式 |
|---|---|---|
| 直接做 | 无业务语义决策、无新增测试义务（排版/注释/配置微调） | 计划模式，不出文档 |
| 本档（plan-goal） | 有决策点或测试义务，单会话可完成，未命中升级触发 | 一份全包计划 → 批准 → goal |
| 升级 | 命中任一升级触发 | lightweight-design 或总控 |
升级触发（命中任一就不许硬塞轻量档）：跨 ≥2 域写入 · 不可逆数据迁移 · 钱/权/数据整链路重构 · 阻塞级决策相互耦合无法一次拍板收敛 · 预计跨会话。
- 判据按「碰了什么」，不按改动量——三行 diff 改掉一条优惠券核销规则不是小任务。
- 死亡线局部小改准入本档：计划开场声明强制标记命中；是否加评审由项目治理策略或指定审查角色决定（对齐
lightweight-design§0.1：死亡线局部改造不升档、升评审强度）。
项目绑定：写计划前按 task-control-doc/references/标准研发流程.md §6.1 在当前项目解析唯一完整的项目研发流程适配器及八槽位。只读取能力、项目路径和执行路由，不申请环境；本档仍保留九节计划载体。
目标环境由有权限的角色明确选择：先列出项目实际支持的环境与能力差异，可以推荐；若本任务已有明确选择，继承其原话与授权锚点，不重复询问。否则提交计划批准前由环境所有者或发布授权人选择唯一环境，不能由 AI 默认，也不能从整份计划获批倒推环境授权。
1. 流程
（可选）调查——亲自读，或有界并行派叶子
（可选）方向对齐——和业务决策负责人对齐结果
│
计划模式：按 §2 模板写一份全包计划
│
项目治理或授权角色可触发对抗评审（AI 永不自行加闸）
│
业务决策负责人批准 = 决策点逐条生效 + 计划冻结落盘（一个文件）
│
执行启动服务：清算 PRE_GOAL，按治理策略合并人工协作窗口
│
生成一条自主执行启动指令（§4 四段式）
│
goal 自主跑到底：M0 启动检查并修执行基础设施 → 施工 → 测试 → 文档同步 → 钩子 → commit → 追加执行记录
│
CANDIDATE_READY ──→ 指定候选验收人终点验收 ──→ 完成
2. 计划模板（9 节）
简单任务半屏写完；每节都有写「无」的权利，但不许整节省略——省略和「无」是两回事：前者没扫过，后者扫过没命中。
| # | 节 | 最低要求 |
|---|---|---|
| 1 | 目标终态 | 可判定，不写动作写终态；必含「已提交、工作树干净」 |
| 2 | 开场声明 | 五项：命中哪几层文档 / 死亡线命中与否（逐条对照项目封闭清单）/ 涉及哪些域 / 是否跨域 / 目标环境；环境附授权角色原话或裁决锚点 |
| 3 | 事实基线 | 改造类必填：计划冻结时的基线 commit，以及在真实代码里读到的关键约束（读过才算，列文件名不算）；未验证的假设显式标注 |
| 4 | 决策点清单 | 每个改变业务结果/契约/持久化语义的选择单列一行：选了什么 / 放弃了什么 / 为什么；死亡线命中项单独标记；禁止多项打包成一次总体同意；无则写「无」 |
| 5 | 改动清单 | 文件/模块级，含接口与 DB 变更 |
| 6 | 测试计划 | ① 命中面判定表：逐面写命中/不命中及理由（矩阵沿用 test-standards §2），不许写「暂不需要」；② AC 表，最低列：编号 / 断言（given-when-then 可简写，但两人照着写脚本行为必须一致）/ 取证形态（实测/推导/替身）/ 执行方式（自动化；手工须写例外理由）/ 规格出处 |
| 7 | 文档同步清单 | 要改的 L1-L7 具体文件 + DDL 快照 + 运行资产台账；有长期回归价值的用例列 L7 落点；无则逐层写「不涉及」 |
| 8 | 执行章程 | 固定要素见 §2.1 |
| 9 | 执行记录 | goal 期间追加专用：一行式飞行日志（时间/类别/改了什么/依据/修复轮次是否 +1）、测试结果、commit SHA、交付证据；末尾有候选闭环行 |
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.
- 29d ago Changed · +3 lines 7280e2d92760
- 1mo ago First seen · 119 lines · 149 tokens per session scan A 52f5399a5867
plan-goal is a skill published in the GitHub repository BackToCimaCoppi/Praxis (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 149 tokens to every session and 3,928 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
browser-tools
Safety rules over the upstream agent-browser skill (scraping ethics, auth, request pacing, local URLs). URL policy is the Claude Code sandbox's job when the operator enables it. Use for browser automation.
rag-retrieval
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, agentic RAG, multimodal RAG, query decomposition, reranking, or pgvector search.
architecture-patterns
Architecture validation and patterns for clean architecture, backend structure enforcement, project structure validation, test standards, and context-aware sizing. Use when designing system boundaries, enforcing layered architecture, validating project structure, defining test standards, or choosing the right…
auto
Intent-classified router, the front door to OrchestKit and the DEFAULT entry point for any goal-shaped request. Classifies a plain-English goal and routes it to the right specialist skill. Routing is never overhead, so use it even when the target skill seems obvious; skip only when already executing inside another…
langgraph
LangGraph 1.x (LTS) Python workflow patterns for state management, delta channels, resilience (node timeouts, error handlers, graceful drain), routing, parallel execution, supervisor-worker, tool calling, checkpointing, human-in-loop, streaming (v2 format), subgraphs, and functional API. Use when building LangGraph…