Borrowing it
Nothing to install: this file belongs to Peiiii/nextclaw. 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/Peiiii/nextclaw/master/.agents/skills/nextclaw-agent-instructions-governance/SKILL.mdgit clone --depth 1 https://github.com/Peiiii/nextclawWrote 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/peiiii/nextclaw/nextclaw-agent-instructions-governance)<a href="https://agentmods.dev/skills/peiiii/nextclaw/nextclaw-agent-instructions-governance"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/nextclaw-agent-instructions-governance/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/peiiii/nextclaw/nextclaw-agent-instructions-governance"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/nextclaw-agent-instructions-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.01041 |
| Opus 5 | $0.00029 | $0.00521 |
| Sonnet 5 | $0.00012 | $0.00208 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
nextclaw-agent-instructions-governance 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 today.
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.
What it actually says
AI 指令系统治理
目标
保持规则可靠、单一 owner、渐进加载和低 token 成本。修改前先对齐 docs/VISION.md、检查工作区和当前规则体积,并识别真正根因是缺失、重复、过宽、过长、过期还是放错层。
分层
AGENTS.md:每轮必须知道的安全与高层边界。.agents/skills/*/SKILL.md:需要参与初始发现的工作流、阶段或独立任务入口。- skill
references/:仅由一个入口拥有、在子场景成立时读取的合同。 .agents/wiki/skills/<group>/<skill>/SKILL.md:按领域分组、被上层显式加载的完整下级 Skill;不参与初始发现。.agents/wiki/knowledge:事实、背景、案例与权威来源索引;不拥有流程或授权。scripts// tests:高信号、低误报、可确定执行的检查。docs/:人类设计、计划和历史;除非入口明确链接,不承担自动硬规则。
每次触发 skill 都必需的内容保留在入口;单 owner 条件内容进 references;两个以上真实入口共享同一独立合同、或能力需要保留可复用 Skill 身份时进入分组 Wiki Skill。不要用 Wiki 隐藏默认必读合同,也不要把只被一个入口使用的材料升级为共享库。
修改顺序
- 区分个案、重复模式和稳定规则;沉淀层级不得高于证据。找 owner 和相邻规则,优先删除、合并、收窄或移动。
- 每个稳定工作域只有一个 workflow root;普通开发由唯一 lifecycle owner 管理。阶段不直接调用其它阶段或回链,独立 skill 不回链上游。
- description 只描述一个稳定意图,不堆“实现/方案/深入/最佳实践”等泛词抢占触发。
- 一个判断分支最多要求一个直接下游;阶段 Skill、下级 Wiki Skill 与知识都只在当前节点加载。
- 规则影响脚本或命令时同步更新;脚本变化也同步 owning 文本。
- 核心阶段使用统一的
development-<stage>命名;只有深度依赖 NextClaw 产品、NCP、Kernel、仓库命令或发布合同的 skill 使用nextclaw-前缀。 - 大型重构写设计并在同批迭代记录中留痕,小措辞不建日志。
条件方法
- 新增、修订、合并或退役意图宏时,读取意图宏维护;调用只读命中定义,不加载维护合同。
- 用户明确要求优化 AI 驱动开发体系,或有效反馈暴露重复、系统性、高影响机制缺口时,读取开发体系演进闭环。
- 修改、提升、下沉、合并或删除规则资产,或者要标记/复核模型能力补丁时,读取规则资产生命周期。
- 任务明确涉及常驻上下文膨胀、渐进加载、重复读取或 Token 成本时,读取上下文与 Token 治理。
- 新增、删除、合并、分组或下沉 Skill,或改变 workflow/阶段/独立入口拓扑时,读取Skill 拓扑与创建门。
普通局部措辞修正不机械加载多份参考;每次只读取当前判断确实需要的方法,不批量预读。
检查
完成前运行 pnpm check:skill-progressive-loading,确认发现预算、顶层/下级 Skill frontmatter、分组边界、Wiki 非发现性、链接、生命周期拓扑、依赖循环和已删除引用;再按改动风险运行治理 ratchet。纯指令 Markdown 不运行 build/tsc/产品冒烟。
最终报告 AGENTS、skill 数、description、discovery 字符和入口体积变化,说明 Wiki、command/script/baseline 是否适用,以及设计/迭代落点。
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · +2 lines e450a2c657df
- 2d ago Changed · +1 lines a81faaf2c186
- 11d ago First seen · 46 lines · 58 tokens per session scan A 5fe7554a3f06
nextclaw-agent-instructions-governance is a skill published in the GitHub repository Peiiii/nextclaw (256 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 1,041 once invoked, about $0.0003 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.
Other skills, from other repositories
openclaw-github-dedupe
Investigate a cluster of GitHub issues and PRs, determine canonical candidates, post duplicate/related status, preserve contributor credit, and execute cleanup actions. Supports autonomous mode for provided-link-only closeout, merge/fix follow-through, changelog, and post-merge issue/PR cleanup.
openclaw-pr-batch-sweep
Select, review, repair, validate, and land batches of up to 20 low-risk OpenClaw contributor pull requests using Vincent's maintainer preferences and bounded sub-agent lanes. Use for "next 20", broad contributor PR sweeps, merge-candidate mining, or continued PR-batch work where drafts, maintainer work, trivial…
tmux-lane-orchestrator
Manage one tmux agent lane from its matching ops pane, inspect live pane state and Codex logs on cold start, and produce concise manager summaries for OpenClaw and adjacent project work.
ghcrawl-cluster-operator
Use when inspecting a ghcrawl SQLite store, pulling GitHub issue/PR data, refreshing summaries, embeddings, and clusters, or extracting one cluster and its evidence through the ghcrawl CLI.
opik-optimizer
Optimize LLM prompts, tools, and agents in Opik using standardized optimizer workflows (prompt optimization, tool optimization, and parameter tuning), dataset/metric wiring, and result interpretation.
org-branch-cleanup
Audit and safely prune stale branches across a GitHub organization with immutable snapshots, conservative merged-PR classification, live SHA/protection/open-PR revalidation, resumable deletion ledgers, and post-delete verification. Use when a maintainer asks to clean up old, dead, merged, bot-created, or abandoned…