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 CCDawn/codex-skills --skill briefbound-huawei-nslb-score-loopgit clone --depth 1 https://github.com/CCDawn/codex-skillsWrote 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/ccdawn/codex-skills/briefbound-huawei-nslb-score-loop)<a href="https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-huawei-nslb-score-loop"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-huawei-nslb-score-loop/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/ccdawn/codex-skills/briefbound-huawei-nslb-score-loop"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-huawei-nslb-score-loop.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 | $0.00051 | $0.01147 |
| Opus 5 | $0.00026 | $0.00574 |
| Sonnet 5 | $0.00010 | $0.00229 |
| Haiku 4.5 | $0.00005 | $0.00115 |
Grade A, and why
briefbound-huawei-nslb-score-loop 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 10d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei NSLB Score Loop
目标
这是 briefbound-score-loop 的 Huawei NSLB 适配层,补充项目识别、工具命令、solver 约束和线上反馈;候选搜索、淘汰和替换仍用通用 score loop。
不得把 skill 内的旧分数、hash 或聊天记忆当成当前事实。最好方案、源码 hash、活跃运行和提交映射须从项目现场读取。
Briefbound task contract
- Context Boundary: 项目根目录、当前 baseline/hash、评价协议、solver 写入面、工具状态和线上反馈。
- Output Contract: 当前状态、下一候选、可比证据、替换决定、提交包或恢复结果。
- Allowed Action: 只在项目授权范围内运行命令和修改隔离 workspace;不静默改主 baseline、ledger、提交映射或线上最佳记录。
- Success Evidence: 当前命令输出、source hash、candidate diff/config、可复现指标、
child_result.json、gate 或短名提交包。 - Stop Condition: source drift 未解释、协议不可比、共享事实源写冲突、child result 无效、提交包无效、线上反馈归属不清或用户暂停。
- Route Out:
briefbound-score-loop、项目工具、briefbound-bug-review、online feedback wait、项目 memory 或 BLOCKED。
统一调用契约
- 只处理 Briefbound task contract;Route Out 仅以 Briefbound task contract 为准。
- 用户可见内容默认中文,先说状态、原因和下一步,不先列 ledger、epoch 或内部枚举。
- 首次出现代理测试时解释:它是用于快速淘汰候选的小测试,不能代替正式分数。
- 只有复杂问题需要时才展开 hash、worker、校准或搜索图;末行写
下一步建议: <一个具体动作>。
Live-State Gate
从 --project、BRIEFBOUND_HUAWEI_NSLB_ROOT 或当前仓库解析根目录,确认 src/Solution.cpp,再定位工具。检查 status、doctor、drift,读取已有 baseline、ledger、online feedback 和 package map;缺失就说明,不新造事实源。协议或 baseline 漂移时先恢复可比性。
工具入口和完整命令分组见 references/huawei-nslb-profile.md。
自适应搜索
根据当前证据选择一个方向:
- 有稳定正向机制:
EXPLOIT,只改一个邻近变量。 - 连续候选重复或停滞:
EXPLORE,从mutation_space.json选择机制不同的 family。 - 本地与线上关系不清、失败原因不明:
DIAGNOSE,先构造区分性 case/trace,不急着改 solver。
候选写清 component、单一机制、预期指标、smallestDecisiveEvaluation、kill condition 和恢复产物。先查重,再跑合法性/编译和最小筛选;无晋升可能就淘汰。
工作重量
QUICK:单候选、单 workspace;无需 epoch、worker pool、attempt card 或 memory 更新。STANDARD:多轮可比候选;复用项目当前 ledger/search history 记录必要结果。FULL:真正独立的并行 lanes、昂贵验证、提交包或线上反馈;才启用 epoch/worker/校准工具。
旧 ledger、search graph、attempt cards 和 failed diffs 是可选事实源,不是每轮流程。
Worker rule
并行收益明确时才创建 worker。worker 只改隔离 workspace,main project 只读;通常只改 src/Solution.cpp 的一个机制。先核对 baseline hash,再编译和最小筛选;命中 kill condition 后保留 diff、指标和原因并停止。完成前写有效 child_result.json,不能自行替换共享 baseline 或线上最佳。
线上反馈与提交
What ships with it
4 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.
- 10d ago First seen · 75 lines · 51 tokens per session scan A 2e40c7a5b992
briefbound-huawei-nslb-score-loop is a skill published in the GitHub repository CCDawn/codex-skills (5 stars, last pushed 28d ago), licensed MIT. It adds 51 tokens to every session and 1,147 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 2026-08-31.
Other skills, from other repositories
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
chinese-code-review
A Chinese-language code-review communication guide with templates and severity levels for review comments.
chinese-commit-conventions
A Chinese-language guide to Conventional Commits, a format for writing consistent Git commit messages, plus related changelog, commit-checking, and commit-helper configuration.
mcp-builder
A guide to building Model Context Protocol (MCP) servers, which let AI assistants use tools and read external data. It covers server structure, tool design, testing, and deployment in TypeScript and Python.
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.