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-narp-stdio-runtime-integration/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-narp-stdio-runtime-integration)<a href="https://agentmods.dev/skills/peiiii/nextclaw/nextclaw-narp-stdio-runtime-integration"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/nextclaw-narp-stdio-runtime-integration.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.01201 |
| Opus 5 | $0.00032 | $0.00600 |
| Sonnet 5 | $0.00013 | $0.00240 |
| Haiku 4.5 | $0.00006 | $0.00120 |
Grade A, and why
nextclaw-narp-stdio-runtime-integration 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 8d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NARP Stdio Runtime Integration
架构合同
- core/kernel/service 只识别通用
narp-stdio，不得硬编码具体 runtime/provider id。 - runtime 身份只存在于
agents.runtimes.entries、installer/repair/marketplace metadata、具体 wrapper package 和显式测试配置。 - Codex、Claude Code 等用户入口保持独立 marketplace skill；公共 NARP 协议实现复用，不合并用户入口。
- host-side stdio client 保持通用；provider 差异属于 agent-side wrapper/bridge。
- 旧 SDK runtime package 可作为 library 复用；除非它有阻塞 bug，不因迁移顺手修改。
- 配置使用
type: "narp-stdio"、config.wireDialect: "acp"和具体config.command。
实现顺序
- 冻结不得触达的通用 client、旧 SDK 和核心边界。
- 复用通用 agent-side wrapper，把
NcpAgentRuntime暴露为 NARP stdio 子进程。 - 为具体 runtime 提供薄 wrapper package 与
<runtime>-narplauncher。 - 通过显式 runtime entry 注册，不在核心注入默认 provider 分支。
- 真实验收同时证明 entry、launcher 可执行、launcher 指向当前待验构建物和模型真实回复。
实现前核对
- 结构：读取目标 package 的 module structure、tsconfig、现有 role 目录和同类 bridge/mapper 落点；新增路径走目录 preflight。
- 上游协议：用最小直连/mock 确认 stream、provider 参数、thinking/reasoning 字段和错误形状。
- 模型路由：确认用户模型 id 是否带 provider 前缀，以及上游前的剥离/映射位置。
- raw event：改 NCP mapper 前先看 SDK/CLI 是否暴露目标增量，还是把 bridge 增量聚合为 snapshot。
- 构建入口：确认 launcher/bin 指向当前源码构建的 dist，不是旧全局版本；改 bridge/wrapper 后重建相关包。
- 配置安全：只核对 apiBase、wireApi、model 和 enabled，不输出 key、token 或 extra headers。
核对后先判断第一个错误 owner：provider bridge、runtime SDK mapper、agent-side wrapper、host-side stdio client 或服务 SSE；owner 不明确时不修改业务代码。
能力验收
完成当前 runtime 集成 slice 后返回生命周期，由 Validation 阶段选择 NCP Chat 冒烟合同。按本次目标断言：
- 文本：固定 marker、text delta 和最终文本；
- 工具：tool-call start/result 与最终 marker；
- 思考：reasoning start/delta/end 与非空 reasoning text；
- 组合：agent runtime 至少一轮 thinking + tool + final text；
- 流式：增量随上游到达，不能完成后一次吐出；
- 连续性：同一产品 session 稳定映射同一 runtime session。触达绑定/恢复时验证首轮 marker、重启、追问，并核对持久化 runtime id；触达模型切换时再验证切换 provider/model 后上下文和 runtime id 不丢。
结论必须写成 runtime + provider/model + capability，不能用一个 provider 代表 runtime，也不能用文本成功代表工具或思考。
分层缩圈
按 provider 直连 -> bridge -> SDK/CLI raw event -> agent-side wrapper -> host-side stdio -> service SSE 找第一个错误 hop；每轮只验证一个假设。若用户问题发生在 dev URL，必须用进程证据确认真实子进程来自当前仓库，而不是转发到全局包。
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.
- 8d ago First seen · 69 lines · 63 tokens per session scan A 1d3ee24af90f
nextclaw-narp-stdio-runtime-integration is a skill published in the GitHub repository Peiiii/nextclaw (256 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 1,201 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.
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…
crabpot-perf-metrics
Interpret Crabpot and OpenClaw performance dashboard metrics, import-loop profiles, runtime profiles, and branch-to-branch perf deltas without over-reading noisy samples.