briefbound-score-loop skillA
briefbound-score-loop is agent-read markdown (skill) from ccdawn/codex-skills: Use when repeated work is governed by an explicit metric, active baseline, candidate search, promotion rule, leaderboard feedback, or submission iteration; do not use for a one-off research check that its current owner can execute directly..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Briefbound Score Loop ## 目标 围绕一个明确指标主动寻找候选，用可比较证据决定是否替换当前最好方案。它负责一条量化优化 lane，不负责整个研究方向或竞赛生命周期。 ## Briefbound task contract - Context Boundary: 主指标、硬约束、当前最好方案、搜索空间、评价协议、预算和允许写入面。 - Output Contract: 下一候选、可比结果、决定、可复用证据和停止/转向信号。 - Allowed Action: 在已确认范围内提出并评估候选；不静默改变指标、数据、基线、预算或提交目标。 - Success Evidence: 精确 baseline/candidate、参数或 diff、命令、数据/seed、主副指标、运行产物和可比性判断。 - Stop Condition: 协议漂移、指标无法解析、候选重复、预算耗尽、连续结果不再提供新信息、写入冲突或安全边界变化。 - Route Out: 继续当前 loop、返回 `briefbound-ai-research-loop`、`briefbound-bug-review`、`briefbound-router` 或 BLOCKED。 ## 统一调用契约 - 只处理 Briefbound task contract；复合任务不吞其他 owner；Route Out 仅以 Briefbound task contract 为准。 - 用户可见内容默认中文，先说结论，再给比较依据。默认使用“替换、淘汰、继续观察、暂时无法比较”等通俗说法；必须保留枚举时写成中文结论加括号，例如“替换当前最好方案（`PROMOTE`）”。 - 复杂指标、代理测试或搜索策略会影响判断时，用一句话解释；不展示内部 trial 账本。有自然闸门（需用户裁决、批准或被外部阻塞）时末行 `下一步建议: <一个具体动作>`，否则声明继续已授权工作。 ## 实验 owner 独占 只有主要未知量是“怎样持续改善一个明确指标”时进入。AI Research 中一次低成本比较由原 owner 直接执行。 分数下降、candidate reject 和 online neutral/worse 是实验结果，不是 TDD RED。metric/parser/schema/seed/shape/NaN/打包出现确定性错误时，临时路由 `briefbound-bug-review`，修复后回到原 lane。 ## Protocol Freeze 比较前冻结以下协议；任何一项变化都先建立新 baseline，不能把前后结果直接相减： - 主指标、越大/越小更好和最小有效提升； - 硬约束与副指标，不能用主指标掩盖合法性、正确性或资源超限； …
Read the whole file at its exact version.
How to install
mdr add ccdawn/codex-skills/briefbound-score-loop@git:20260916.292b0acmdr add ccdawn/codex-skills/briefbound-score-loop@sha256:f26a125f09977721Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_u4zghny574pcehjk)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260916.292b0ac latest | 2026-09-16 | 292b0ac | 6,121 B | A | view · diff |
| git:20260813.dec1d14 | 2026-08-13 | dec1d14 | 6,018 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6121 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
ccdawn/codex-skills · 6 stars · license MIT · pushed 2026-09-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_u4zghny574pcehjk GET https://markdownregistry.com/api/v1/resolve?ref=ccdawn/codex-skills/briefbound-score-loop GET https://markdownregistry.com/api/v1/blob/f26a125f09977721d961ec32f9e5195f8ec3d6f797b8e55a8059d4e28d2a8d33
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.