briefbound-score-loop

briefbound-score-loop is a skill for Claude Code, Codex from CCDawn/codex-skills. It costs 49 tokens per session (1,545 once invoked), scanned A, original, MIT.

A metric-driven workflow for repeatedly testing candidate solutions against a fixed baseline and keeping a replacement only when the evidence supports it.

In plain words
What is it for?
Use it for experiments, model or prompt improvements, competition submissions, and other work where candidates are compared by a defined score.
Why use it?
It prevents changes to the measurement rules or comparison conditions from making results misleading.

Skill for Claude CodeCodex

Part of the briefbound-skills plugin — 30 skills shipped together

Install

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.

agentmods
npx agentmods add skills/ccdawn/codex-skills/briefbound-score-loop
Any agent
npx skills add CCDawn/codex-skills --skill briefbound-score-loop
Clone the repo
git clone --depth 1 https://github.com/CCDawn/codex-skills

Made for: Claude Code, Codex.

Or install briefbound-skills, the plugin that ships this one along with the rest of its 30 skills.

Wrote 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.

agentmods badge for briefbound-score-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-score-loop.svg)](https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-score-loop)
Your own site
<a href="https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-score-loop"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-score-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,545 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00049 $0.01545
Opus 5 $0.00024 $0.00772
Sonnet 5 $0.00010 $0.00309
Haiku 4.5 $0.00005 $0.00154

Measured 4d ago against content hash 066c366a4fa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

briefbound-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 4d 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.

skills/competition/briefbound-score-loop/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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、返回 briefbound-competition-research-lifecyclebriefbound-bug-reviewbriefbound-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。末行写 下一步建议: <一个具体动作>

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;
  • baseline 的 commit/hash/config;
  • 数据、case、seed、运行环境和评价命令;
  • 单候选预算、总预算和停止条件。

若目标确实有多个指标,先指定主指标与硬约束;只有用户明确接受综合规则时才做加权,不临时拼一个总分。

Search Policy

每轮先选择一种搜索意图,再生成候选:

  • EXPLOIT:已有稳定正向信号时,在当前最好方案附近做小步改动。
  • EXPLORE:结果停滞或局部空间已重复时,尝试机制不同的方向。
  • DIAGNOSE:噪声、代理指标或失败原因不清时,先设计能区分原因的检查。

把变量写成可判断的搜索空间:类别、顺序、数值或结构变化。候选必须有一个主要因果机制和唯一指纹;已做过的同机制、同方向、同边界候选直接跳过。随机变化若不能回答问题,也不进入队列。

ASK -> FILTER -> TELL

  1. ASK:根据当前证据提出一个候选,写清机制、预期信号、smallestDecisiveEvaluation 和 kill condition。
  2. FILTER:先做构建、合法性、成本和最小决定性检查。即使最乐观也过不了替换标准时,立即 PRUNE;诊断候选则按是否回答问题判断。
  3. 通过初筛后跑代表性评价;昂贵完整评价只留给仍可能晋升的候选。
  4. TELL:记录结果、可比性、机制判断和副作用,再更新下一轮的 EXPLOIT / EXPLORE / DIAGNOSE 选择。
  5. 没有新变量、新证据或校准价值时停止,不用更多试验掩盖平台期。

内部 trial 可标记 ASKED / RUNNING / PRUNED / COMPLETE / FAILED;用户通常只需要知道结果和原因。

决定规则

  • PROMOTE:可比较,主指标超过有效提升线,硬约束通过,代表性结果支持替换 baseline。
  • REJECT:可比较但未过线,或副作用越过已确认边界。
  • HOLD:方向有信息价值,但样本、稳定性或代表性不足,下一项验证明确。
  • BLOCKED:协议漂移、证据缺失或结果不可解析,当前无法安全比较。

Read the full file on GitHub · 96 lines

Files

What ships with it

2 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.

Changes

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.

  1. 4d ago First seen · 96 lines · 49 tokens per session scan A 066c366a4fa0

Subscribe to this mod's changes

briefbound-score-loop is a skill published in the GitHub repository CCDawn/codex-skills (4 stars, last pushed 22d ago), licensed MIT. It adds 49 tokens to every session and 1,545 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

chinese-documentation

中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。.

jnMetaCode/superpowers-zh · 62 tokens

chinese-git-workflow

国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。.

jnMetaCode/superpowers-zh · 69 tokens

chinese-code-review

中文 review 沟通参考——话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发。.

jnMetaCode/superpowers-zh · 62 tokens

chinese-commit-conventions

中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用,不要根据上下文自动触发。.

jnMetaCode/superpowers-zh · 65 tokens

mcp-builder

MCP 服务器构建方法论 — 系统化构建生产级 MCP 工具,让 AI 助手连接外部能力.

jnMetaCode/superpowers-zh · 32 tokens

systematic-debugging

Skill "systematic-debugging" from jnMetaCode/superpowers-zh, covering 系统化调试, 概述, 铁律, 何时使用 and 四个阶段.

jnMetaCode/superpowers-zh · 24 tokens