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 yangKJ/think-tank-skill --skill think-tankgit clone --depth 1 https://github.com/yangKJ/think-tank-skillWrote 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/yangkj/think-tank-skill/think-tank)<a href="https://agentmods.dev/skills/yangkj/think-tank-skill/think-tank"><img src="https://agentmods.dev/badge/skills/yangkj/think-tank-skill/think-tank/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/yangkj/think-tank-skill/think-tank"><img src="https://agentmods.dev/badge/skills/yangkj/think-tank-skill/think-tank.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 | $0.00045 | $0.03348 |
| Opus 5 | $0.00023 | $0.01674 |
| Sonnet 5 | $0.00009 | $0.00670 |
| Haiku 4.5 | $0.00005 | $0.00335 |
Grade A, and why
think-tank 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 — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.
think-tank Skill
定位
think-tank 是一个跨平台、可复用的高阶 Skill,用于多角色信息收集、协作分析、讨论审议与结论汇总。
它不是工具合集,不复制外部 skills;它负责任务理解、协议执行、角色组织、能力编排和最终汇总。
Skill 和运行目录边界
think-tank 的 skill 本体只能是当前安装位置中的 SKILL.md、协议、profiles、recipes、routing、platform adapters 和 runtime 文件。
.think-tank/ 是运行配置、provider preflight、runs、memory 和 artifacts 存储目录,不是 skill 目录。不要把 .think-tank/ 放进 .codex/skills/ 或 .claude/skills/。
provider 边界仍必须遵守:selection 不等于 invocation,真实 provider 调用前必须有明确 dispatch decision、权限确认和结果回收。
3.0 Skill Experience Layer
think-tank 3.0 增加面向 agent 的使用体验层,用来回答三个问题:
- 这个任务是否应该使用 think-tank?
- 使用前需要形成什么 invocation contract?
- 当前任务应该加载哪些最小协议、mode、recipe、profile、platform 或 provider 文档?
先按以下协议做判断:
protocol/skill-trigger-intelligence.md
protocol/skill-invocation-contract.md
protocol/runtime-profile-contract.md
protocol/progressive-disclosure.md
触发词、别名、平台快捷语和 provider 偏好不属于公开 core 的内置规则。它们应由用户自己的 YAML policy 或平台 adapter 定义。公开 core 只能提供 intent 识别原则、trigger category 示例和 policy schema。
当触发来源不明确时,先输出 skill_route_decision,并标注:
policy_source: protocol_default
trigger_status: inferred_intent_only
何时使用
当用户任务满足任一条件时,使用 think-tank:
- 需要多渠道信息收集
- 需要多个角色分别判断
- 需要讨论、审议、观点碰撞或决策
- 需要审查产物、发现问题或验收
- 需要策略、路线、产品或架构判断
- 需要把复杂资料汇总为行动建议
以下只是可被用户 YAML policy 采用的 intent 短语示例,不是 think-tank core 的内置触发规则:
- 研究:
研究一下、深度研究、全面分析 - 竞争:
竞品分析、竞争分析、竞品调研 - 市场:
市场调研、行业分析、用户需求 - 技术:
技术调研、方案调研、可行性分析 - 反馈:
舆情分析、用户反馈、评论分析 - 决策:
开会讨论、讨论一下 - 审查:
审查、review、验收、找问题 - 策略:
制定策略、路线图、行动方案
平台无关的 intent 路由见:
protocol/intent-routing.md
protocol/skill-trigger-intelligence.md
跨项目任务配方见:
recipes/
其中 research-to-video 覆盖选题研究、资料调研到视频 brief、分镜、媒体执行记录和质量门禁。
Codex 平台只负责把这些 intent/recipe 映射到当前可用能力,见:
platforms/codex/trigger-routing.md
不应强行使用 think-tank:
- 简单事实查询
- 单页摘要
- 明确的一步命令
- 不需要多角色或证据判断的任务
执行顺序
1. 解析任务
提取:
- 用户目标
- 已知上下文
- 约束
- 成功标准
- 是否需要实时信息
- 期望输出
What ships with it
60 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.
- assets/brand/cookbook-image2.png 1457 KB
- assets/brand/council-card-image2.png 1264 KB
- assets/brand/first-run-guide-image2.png 1270 KB
- assets/brand/operator-manual-image2.png 1347 KB
- assets/brand/progression-guide-image2.png 1290 KB
- assets/brand/provider-ecosystem-image2.png 1329 KB
- assets/brand/README.md 587 B
- assets/brand/research-card-image2.png 1181 KB
- assets/brand/research-os-memory-runtime-image2.png 118 KB
- assets/brand/review-card-image2.png 1263 KB
- assets/brand/think-tank-hero-cn-image2.png 1318 KB
- assets/brand/think-tank-hero-image2.png 1351 KB
- assets/brand/think-tank-hero-v2-image2.png 109 KB
- assets/prompts/cookbook-image2-prompt.md 164 B
- assets/prompts/first-run-guide-image2-prompt.md 173 B
- assets/prompts/hero-image2-prompt.md 251 B
- assets/prompts/hero-v2-cn-image2-prompt.md 207 B
- assets/prompts/hero-v2-image2-prompt.md 217 B
- assets/prompts/operator-manual-image2-prompt.md 153 B
- assets/prompts/progression-guide-image2-prompt.md 196 B
- assets/prompts/provider-ecosystem-image2-prompt.md 199 B
- assets/prompts/README.md 186 B
- assets/prompts/research-os-memory-runtime-image2-prompt.md 197 B
- assets/README.md 457 B
- capabilities/browser-automation.md 1.3 KB
- capabilities/knowledge-persistence.md 1.0 KB
- capabilities/media-processing.md 1.1 KB
- capabilities/media-production.md 5.4 KB
- capabilities/README.md 1.5 KB
- capabilities/slot-contract.md 2.5 KB
- capabilities/social-listening.md 1.1 KB
- capabilities/source-acquisition.md 1.3 KB
- docs/adoption-roadmap.md 2.2 KB
- docs/agent-compatibility-matrix.md 2.3 KB
- docs/agent-council-full-inventory.md 3.1 KB
- docs/agent-council-history-index.md 1.7 KB
- docs/agent-council-runtime-migration.md 2.2 KB
- docs/architecture.md 5.1 KB
- docs/browser-automation-integration-report.md 1.9 KB
- docs/capability-degradation-report.md 2.1 KB
- docs/capability-validation-roadmap.md 2.3 KB
- docs/claude-code-installation.md 1.4 KB
- docs/claude-code-preflight.md 6.2 KB
- docs/claude-code-validation-report.md 5.5 KB
- docs/codex-acceptance.md 3.8 KB
- docs/codex-external-skills-installation.md 3.4 KB
- docs/codex-installation.md 2.3 KB
- docs/codex-installed-skill-validation.md 2.2 KB
- docs/codex-readiness-matrix.md 4.7 KB
- docs/codex-research-agent-takeover-test-plan.md 2.4 KB
- docs/codex-runtime-verification-matrix.md 4.2 KB
- docs/codex-true-multi-agent-validation.md 1.8 KB
- docs/codex-validation-report.md 7.1 KB
- docs/concepts/memory-runtime.md 359 B
- docs/concepts/protocol-overview.md 427 B
- docs/concepts/provider-evidence.md 331 B
- docs/concepts/research-os.md 346 B
- docs/cookbook.md 2.9 KB
- docs/external-capability-testing-strategy.md 2.0 KB
- docs/external-skill-interoperability.md 2.7 KB
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 · 393 lines · 45 tokens per session scan A fb090cac1fc5
think-tank is a skill published in the GitHub repository yangKJ/think-tank-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 3,348 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
create-custom-grader
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.
api-caller
Call any REST API dynamically. Make GET, POST, PUT, DELETE requests to any endpoint with custom headers and JSON body.
calculator
Evaluate mathematical expressions and unit conversions. Handles arithmetic, percentages, exponents, and common unit conversions (temperature, distance, weight). No external dependencies.
task-list
Required for 4+ step requests; add tasks at start and update status after each step.
text-analyzer
Analyze text content and produce statistics including word count, line count, character count, most frequent words, and readability metrics. Works on any plain text input provided inline or from a file path.
chatbot
Use when a support or sales bot on a live website must behave: persona/system prompt, grounding so it cannot invent prices or policy, jailbreak and injection defense, the human handoff, launch metrics and kill switch. NOT the agent loop or RAG index under it (that is building-agents), NOT a human answering one ticket…