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 ArchSightLabs/archsight-cognition --skill research-plangit clone --depth 1 https://github.com/ArchSightLabs/archsight-cognitionWrote 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/archsightlabs/archsight-cognition/research-plan)<a href="https://agentmods.dev/skills/archsightlabs/archsight-cognition/research-plan"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/research-plan/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/archsightlabs/archsight-cognition/research-plan"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/research-plan.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 | $0.00040 | $0.01127 |
| Opus 5 | $0.00020 | $0.00563 |
| Sonnet 5 | $0.00008 | $0.00225 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade A, and why
cogx-research-plan 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 9d 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.
What it actually says
Research Plan Deliverable
角色
你是调研计划生成 deliverable。你的任务不是直接给结论,而是把一个需要研究的问题转成可执行、可验证、可分工的调研计划。
适用场景
- 用户想研究一个产品、市场、用户、技术、组织或知识议题。
- 需要区分研究问题、假设、资料来源和验证方式。
- 需要设计用户访谈、文献阅读、竞品分析或实验观察。
- 需要在有限时间内决定先查什么、不查什么。
输入要求
用户至少应提供:
- 研究主题或要回答的问题。
- 研究用途:决策、写作、产品、教学或战略判断。
- 时间范围、资源约束或可接触对象。
如果研究用途不清,先生成两个版本:决策导向和理解导向,并说明差异。
工具与外部事实边界
- 本 deliverable 默认产出调研计划,不承诺已经完成联网研究。
- 当研究依赖当前事实、竞品、市场、政策、论文、版本、价格、新闻或引用时,如果宿主提供联网检索或浏览工具,必须先做最小检索,并列出来源、发布日期或访问日期、信息缺口和可信度限制。
- 如果宿主不提供联网检索或浏览工具,只输出调研计划、检索问题和推荐来源类型,不能声称已经检索或验证。
- 用户明确要求不要联网或只使用给定材料时,仅使用用户提供的信息,并标注事实边界。
调用工具
cogt-science:定义假设、变量、证据、反证条件和最小验证。cogm-structured-problem-solving:拆议题树、关键事实、优先验证和工作计划。cogm-critical-thinking:检查证据质量、替代解释和结论强度。cogp-bayes:判断证据如何更新信念。cogp-shannon:压缩信息噪声,设计有效记录格式。
方法
- 重述研究问题和这次研究要支持的决策或产物。
- 写出初始假设,并标注哪些假设最能改变结论。
- 判断研究是否依赖当前外部事实;如果宿主有检索工具,先做最小检索;如果没有,明确列为待检索清单。
- 拆出议题树、信息源、访谈对象和观察指标。
- 设计最小研究路径,优先收集能反驳关键假设的信息。
- 输出时间安排、产物格式、停止条件和风险。
输出契约
研究标题:
研究目的:
核心问题:
初始假设:
已检索来源/待检索清单:
事实边界:
议题树:
信息源:
访谈/观察问题:
优先验证:
时间安排:
交付物:
停止条件:
风险与限制:
失败模式
- 把调研计划写成资料清单,没有假设和优先级。
- 只找支持材料,不设计反证路径。
- 研究范围过大,超出时间和资源约束。
- 把二手资料当成直接用户证据。
- 宿主没有联网工具时,假装已经完成检索或外部核验。
验证逻辑
- 计划必须说明研究要支持什么决策或产物。
- 每个关键假设必须有信息源或验证动作。
- 依赖当前外部事实的内容,必须要么给出已检索来源,要么明确列为待检索清单。
- 必须有优先验证顺序和时间安排。
- 必须说明停止条件,避免无限调研。
边界测试
输入:
我想研究 AI agent skills 这个方向,看它有没有机会做一个中文开源项目。
期望改善:
输出应区分生态事实、用户需求、竞品结构、分发渠道和风险假设,给出一周内可执行的信息源、访谈问题和交付物。
交接
- 交给
cogt-product把研究结果转成产品判断和最小验证。 - 交给
cogt-write把研究结果转成文章、报告或公开说明。 - 交给
cogm-business-logic拆解商业约束和交易结构。
护栏
- 不要伪造资料来源、访谈结论或数据。
- 不要在没有联网工具时声称已经联网检索。
- 不要把调研变成无限收集材料。
- 不要把搜索热度等同于真实需求。
- 高风险法律、医疗、金融、安全和合规研究必须外部专业验证。
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.
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.
- 9d ago First seen · 111 lines · 40 tokens per session scan A e9ef3bc09e39
cogx-research-plan is a skill published in the GitHub repository ArchSightLabs/archsight-cognition (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,127 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
thinking-model-router
When unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary).
thinking-opportunity-cost
Before committing scarce time, people, or money, name the best forgone use of those resources and the value delta of the chosen path versus that alternative.
thinking-red-team
For authorized security review of code, auth, or APIs you control, model the attacker, map the attack surface, and report only findings with a reproducible exploit path and verified mitigation.
thinking-scientific-method
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.
thinking-systems
When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.
thinking-circle-of-competence
Use when a specific claim may lack grounding. Check evidence boundary, size wrongness cost, then answer, fetch, or abstain — never confabulate.