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-research-rigor-reviewgit 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-research-rigor-review)<a href="https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-research-rigor-review"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-research-rigor-review/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-research-rigor-review"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-research-rigor-review.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 | $0.00061 | $0.01397 |
| Opus 5 | $0.00030 | $0.00698 |
| Sonnet 5 | $0.00012 | $0.00279 |
| Haiku 4.5 | $0.00006 | $0.00140 |
Grade A, and why
briefbound-research-rigor-review 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 11d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
研究严谨性审查
目标
判断“现有证据到底允许我们说什么”,防止偶然涨分、评价泄漏、错误归因或过度外推进入 active baseline 和正式 claim。
本 skill 是关键结论的 gate,不是每条实验 lane 的固定尾声。普通候选由 briefbound-score-loop 自行 gate;只有结论将影响研究方向、论文、发布或高成本投入时才触发。
Briefbound task contract
- Context Boundary: 待审结论、研究问题、baseline、实验协议、数据与 split、对照/消融、重复结果、artifact 和适用范围。
- Output Contract: 按证据排序的 findings、允许表述、缺失证据、严谨性判定和最小补强动作。
- Allowed Action: 只读审查证据并运行必要的低风险复核;未经授权不修改研究代码、metric、数据或 claim 来源。
- Success Evidence: 可定位的命令、结果、表格、diff/config、统计信息、对照、复现记录和来源映射。
- Stop Condition: 关键 artifact 缺失、baseline/协议无法确认、数据泄漏或评价漂移未排除、结果不可复现,或结论与证据对象不一致。
- Route Out: 返回
briefbound-ai-research-loop、返回briefbound-score-loop补实验、路由确定性 bug owner、限定/接受结论,或 BLOCKED。
统一调用契约
- 只处理 Briefbound task contract 范围;不匹配时回
briefbound-router或更具体 owner,复合任务不吞其他 owner。 - 用户可见内容默认中文,完成只报状态、产出、证据和剩余风险;代码、命令、路径、错误原文、API/协议、skill 名和枚举保留原样;Route Out 仅以 Briefbound task contract 为准,末行写
下一步建议: <一个具体动作>。
触发闸门
满足任一条件才进行完整审查:
- 候选将成为重要 best-known 结果、改变研究方向,或晋升依据超出普通 score gate;
- 结论准备进入论文、报告、README、发布说明或对外宣传;
- 结果反直觉、与先验冲突或将触发研究方向转向;
- 下一步需要显著更多算力、数据、人工或外部提交机会;
- 用户明确要求科研审查、证据审计或 claim 校准。
单次普通失败、低成本 smoke 或尚未形成结论的探索只做局部检查,不输出完整矩阵。
审查方法
先写出一个可审查句子:
在 <数据/协议/范围> 下,<候选> 相比 <baseline> 产生 <观测>,因此支持 <最窄解释>。
然后只检查与当前 claim 有关的维度:
- 证据相关性:metric 和实验是否直接测量 claim,还是只使用 proxy。
- 可证伪性:是否存在能推翻解释的对照、消融或结果;失败条件是否预先明确。
- 范围校准:结论是否超出数据、seed、模型规模、任务、硬件或评价协议。
- 归因一致性:一个主要机制是否被隔离;是否混入数据、参数量、训练预算或实现差异。
- 探索完整性:负结果、异常值和冲突证据是否被保留;是否只报告赢家。
- 方法严谨性:baseline、split、泄漏、重复、方差、统计、复现和 artifact 是否足以支持风险等级。
无需机械输出六项。没有 finding 的维度一句结论即可;有问题时给出精确证据和影响。
严重度与判定
Findings 按影响排序:
P0 BLOCKER:证据无效或不可定位,例如泄漏、错误 metric、错误 baseline、结果无法复现。P1 MAJOR:会改变 claim 或方向,例如缺关键对照、混杂变量、强 seed/split 敏感。P2 LIMITATION:结论仍可保留但必须限定范围或降低置信度。P3 IMPROVEMENT:不会改变当前结论的可选增强。
最终只给一个 verdict:
ACCEPT:证据足以支持当前窄 claim;QUALIFY:保留结论,但必须收窄表述或明确限制;REJECT:当前证据不支持该解释或晋升;BLOCKED:缺少决定性 artifact,无法审查。
审查不以“测试通过”替代研究证据,也不因一个指标上涨默认 ACCEPT。
What ships with it
1 file 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.
- 11d ago First seen · 105 lines · 61 tokens per session scan A 79b9788a4cb0
briefbound-research-rigor-review is a skill published in the GitHub repository CCDawn/codex-skills (6 stars, last pushed 28d ago), licensed MIT. It adds 61 tokens to every session and 1,397 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
brainstorming
A brainstorming workflow for turning an idea into an agreed design before implementation. It requires exploring the project, asking clarifying questions, comparing options, documenting the design, and getting user approval.
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.