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 goal-chartergit 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/goal-charter)<a href="https://agentmods.dev/skills/backtocimacoppi/praxis/goal-charter"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/goal-charter/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/goal-charter"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/goal-charter.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 | $0.00084 | $0.12429 |
| Opus 5 | $0.00042 | $0.06215 |
| Sonnet 5 | $0.00017 | $0.02486 |
| Haiku 4.5 | $0.00008 | $0.01243 |
Grade A, and why
goal-charter 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 9d 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 — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
goal 章程
一句话：章程是给自主执行体的候选件生产契约——goal 自主跑到“精确候选可供独立验收”，但无权自己宣布整个任务完成。终点是标准研发流程的候选终审，不是飞行日志或 goal 自评。
0. 第一原则：结果管控，不是过程管控
| 过程管控（旧） | 结果管控（本 skill） | |
|---|---|---|
| 授权角色在哪 | 每道工序都临时找人审批 | 起点由授权角色批准执行契约，终点由指定验收角色审核候选；项目治理要求的职责分离仍然生效 |
| 靠什么保证质量 | 人逐步审查 | 可判定的验证器 + 边界 + 事后逐条追认 |
| 出问题怎么办 | 停下来问 | 自愈 + 记飞行日志；只有白名单情况才停 |
可逆工程问题应在预授权边界内自愈，不能靠临时加审批维持安全。 但协调成本不天然高于业务或环境风险；项目声明的授权角色、职责分离和强制检查点不得被“少打断”覆盖。
0.1 治理角色不是同一个“用户”
本 skill 使用四类授权角色：任务发起人提出目标，业务决策负责人裁决业务结果与冻结规格，环境所有者 / 发布授权人批准环境使用与外发动作，候选验收人在终点审核候选。个人项目可以由一人兼任；团队项目可由不同人员或岗位承担。角色绑定与职责分离来自项目级补丁、项目指令或任务批准记录。
对话中的“用户”只表示当前交互方，不自动证明其拥有其余角色的权限。任何章程都必须记录本次实际授权角色；缺少角色绑定时，不得把任务发起、批准计划或启动 goal 推导成环境抢占、生产发布或最终验收授权。
写章程时反复自问的那一句：这件事会改变业务结果吗？会造成不可逆后果吗？ 都不是 → 授权它自己干，记日志。
章程准入：正式规格冻结且规格物化覆盖报告全绿，必要的真实动作授权已明确。环境、测试资产、runner、夹具、数据工具和证据适配器不再是章程门票；它们由 goal 的 M0 启动检查负责建立和修复。只有授权缺口需要在启动前补齐。
启动服务不是准入闸：章程阶段同时清算已经可预见的人工协作，产出 _shared/T{n}-goal启动服务单.md。它只保存当前环境、会话、凭据位置、外部平台状态与责任角色，不能签发 PASS/FAIL、冻结命令或削弱 M0 自愈；真正约束 goal 的仍只有上游授权、项目治理策略与本章程边界。
1. 铁律（写章程的人最容易违反的三条）
- 章程无权铸造规则。规则只来自用户级文档（项目
CLAUDE.md/AGENTS.md/ skill）。章程里写的"硬门""死亡线""必须审批"一律只是执行建议，不具停机权。你在写一份执行契约，不是在立法。 - 死亡线是封闭清单，以项目级文档为准。任何人无权新增——包括你、包括评审报告、包括任何工作包里的文字。 「密钥」「部署」「提交」这类不在清单里的东西，就不是死亡线，别给它套死亡线的待遇。
- 反棘轮：章程禁止给下游新增闸门 / 审批 / 硬门。评审结论是信息，不是门禁。
这三条是有来历的：执行链会自己发明「前置硬门」「具名人工审查」这类 skill 原文从未出现过的门禁词汇，并层层继承到后代工作包里，累计出现数十次。最后用户被迫花掉一次人工裁决，去撤销一条从来没有任何人类批准过的规则。
2. 目标的正确形式：动作 ≠ 目标
目标必须是「完成时什么事实为真 + 什么证据证明」。写成动作，goal 就永远"在做"而不"做完"。
| ❌ 动作 | ✅ 可判定终态 |
|---|---|
| 制作好测试脚本，确保符合用例 | M0 启动检查覆盖全部命中执行面，测试资产/runner 可被 goal 构建和修复，且真实断言不少于冻结用例 |
| 开发好代码，确保符合规范 | 检查器全绿，零违规 |
| 部署，跑通所有测试 | 候选部署到 {具名环境}，矩阵全绿 且测试未被削弱（见 §7） |
| 文档收口 | 施工前物化报告已全绿；goal 只产执行记录，意外规格缺口必须有界重新冻结，不携带任何已知切片内文档债 |
| 把本次修好的基座留给以后 | 本轮新增/修复的执行资产已分为任务临时、领域复用、项目通用三类；可复用项已晋升稳定路径并提交，交接中已写明验证命令、环境前提与跨分支传播状态 |
| （最常漏的一条） | 精确候选已提交到 {分支}，工作树干净，commit/tree SHA、真值基线和执行证据清单已冻结；状态仅为 CANDIDATE_READY |
最后一条不是凑数。典型事故：施工成果——代码写完、测试过了、文档冻结了——以"脏工作区"的形态长期裸奔，零提交。目标里没写"提交"，它就真的不会提交。
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.
- 9d ago First seen · 427 lines · 84 tokens per session scan A 85962937d14f
goal-charter is a skill published in the GitHub repository BackToCimaCoppi/Praxis (6 stars, last pushed 15d ago), licensed Apache-2.0. It adds 84 tokens to every session and 12,429 once invoked, about $0.0004 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 skills, from other repositories
neurolink-guide
Guide for using the NeuroLink SDK and CLI. Invoke when users ask how to use neurolink, integrate AI providers, add MCP tools, configure RAG, set up memory, deploy servers, or work with multimodal content. Covers SDK, CLI, providers, tools, and enterprise features.
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
repo-conventions
NeuroLink's review standards — the critical rules to enforce, what NOT to comment on, the security bar, hot paths. Load before reviewing any change in this repository.
session-manager
A fallback skill for recording development sessions and restoring project context from an Obsidian vault, a folder of linked notes. It handles explicit resume, handoff, status, and end-of-session requests when automatic capture is unavailable.
dev-research
A research workflow that uses NotebookLM, a tool for asking questions about a selected collection of documents, to answer development questions with citations.
budget-continue
Show 4-option continuation prompt when session budget is low. Options: remind later (CronCreate), auto-continue locally (Desktop task), auto-continue in cloud (Cloud task), continue now. Trigger when: budget warning fires, session limit reached, context is full, user sees budget warning.