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-creative-toolboxgit 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-creative-toolbox)<a href="https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-creative-toolbox"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-creative-toolbox/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-creative-toolbox"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-creative-toolbox.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 | $0.00043 | $0.01323 |
| Opus 5 | $0.00022 | $0.00661 |
| Sonnet 5 | $0.00009 | $0.00265 |
| Haiku 4.5 | $0.00004 | $0.00132 |
Grade A, and why
briefbound-creative-toolbox 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creative Toolbox
目标
根据用户所处阶段选择一个合适的创意方法，产出少量具体、非显而易见且能继续行动的想法。重点是改变机制或观察角度，不是把普通建议包装成概念卡。
Briefbound task contract
- Context Boundary: 用户目标、当前材料、创意阶段、领域、约束和明确非目标。
- Output Contract: 选用的方法、少量具体候选、真实失败方式、推荐方向和第一步。
- Allowed Action: 生成、改写、比较和筛选想法；外部调研、实现、资产或代码写入需路由对应 owner。
- Success Evidence: 每个保留候选绑定当前情境，说明具体机制、适用原因、失败方式和可执行第一步。
- Stop Condition: 创意阶段仍有高影响歧义、上下文不足以产生具体候选、用户已选择方向，或请求进入实现。
- Route Out:
briefbound-planning、briefbound-feature-reuse-research、briefbound-evaluation、具体实现 owner，或briefbound-router。
统一调用契约
- 用户可见内容默认中文，先给可用想法，不汇报内部路由过程；Route Out 仅以 Briefbound task contract 为准。
- 方法名会帮助复用时才展示，并用一句话解释它如何改变本轮思考；不列一串术语。
- 默认给 3 个候选，不用空话凑数。末行写
下一步建议: <一个具体动作>。
Method Router
先判断阶段，再选方法；一次默认只用一个方法：
| 阶段 | 用户信号 | 默认方法 | 目的 |
|---|---|---|---|
GENERATE |
还没有方向 | 约束碰撞 | 用真实材料和限制生成方向 |
EXPAND |
已有一个想法，想看变化 | 机制变异 | 改用户、触发、媒介、尺度或反馈 |
SELECT |
已有多个选项 | 事前验尸/反向检验 | 用失败原因拉开差异 |
UNBLOCK |
卡住或循环重复 | 反转 | 暂时颠倒关键假设以找新入口 |
SUBVERT |
太安全、太常规 | 挑衅约束 | 先制造不合理命题，再翻译成可用机制 |
REFINE |
方向可用但不够锋利 | 矛盾求解 | 明确冲突并重新安排关系 |
SYNTHESIZE |
有大量笔记或观察 | 聚类命名 | 找重复结构、异常项和未命名主题 |
NAMING |
需要命名 | 命名锻造 | 从机制、张力和记忆点生成名称 |
若用户直接指定方法就使用它。只有两个信号确实冲突且单一方法无法处理时，最多组合两个，并说明各自作用。阶段不清且会改变方法时只问一个问题；否则基于当前材料直接开始。
需要时才读 references/full-toolbox.md。Perspective Jury 和 role-deck.md 仅用于用户明确要求的深度对抗评估。
Anti-Obvious Gate
内部先拒绝前 3 个显而易见的答案；AI、效率、习惯、旅行、健身等同质化主题拒绝前 5 个。废案通常不展示。
保留候选必须同时满足：
- 绑定用户的真实材料、限制或张力；
- 描述具体机制，不用“平台、生态、AI 赋能”代替机制；
- 与其他候选在核心做法上不同；
- 至少一个今天就能开始验证；
- 说明一个真实失败方式或不适用场景。
“怪”不是质量。无法说明为什么现在有用、为谁有用或怎样开始的怪想法应淘汰。
最小流程
- 提取阶段、领域、具体问题和硬约束。
- 选择一个方法，并用它生成足够多的内部草案。
- 运行 Anti-Obvious Gate，删除换皮、重复和只改命名的想法。
- 默认保留 3 个差异最大的候选，其中至少一个现实可做、一个打破常规。
- 每个候选说明机制、为什么适合、失败方式和第一步。
- 推荐一个方向并说明选择依据；用户选中后停止继续发散，路由到深化或实现。
输出
简单任务直接给候选。复杂任务可用：
本轮方法: <方法；一句话解释>
1. <候选名称或一句话定义>
- 怎么运作: <具体机制>
- 为什么适合: <与当前情境的连接>
- 可能失败在: <真实失败方式>
- 第一步: <可执行动作>
我的建议: <一个候选及理由>
下一步建议: <一个具体动作>
命名任务改为输出 名称 / 词源或构成 / 传达的机制 / 容易误解之处；选择任务允许只返回一个明确结论，不硬凑三个新想法。
What ships with it
3 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.
- 8d ago First seen · 92 lines · 43 tokens per session scan A 48355d95b5d2
briefbound-creative-toolbox is a skill published in the GitHub repository CCDawn/codex-skills (4 stars, last pushed 26d ago), licensed MIT. It adds 43 tokens to every session and 1,323 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.
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.
desktop-brand-builder
Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop-shell.
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-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.
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.