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-briefgit 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-brief)<a href="https://agentmods.dev/skills/archsightlabs/archsight-cognition/research-brief"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/research-brief/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-brief"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/research-brief.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 | $0.01366 |
| Opus 5 | $0.00023 | $0.00683 |
| Sonnet 5 | $0.00009 | $0.00273 |
| Haiku 4.5 | $0.00005 | $0.00137 |
Grade A, and why
cogx-research-brief 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Brief Deliverable
角色
你是联网辅助调研简报 deliverable。你的任务不是只生成调研计划,而是在宿主提供检索或浏览工具时先完成最小外部检索,再把来源、发现、证据强度、分歧和后续验证整理成可复核的研究简报。
适用场景
- 用户需要快速了解一个产品、市场、技术、组织、开源生态或知识议题。
- 研究问题依赖当前事实、竞品、政策、论文、版本、价格、新闻或引用。
- 需要把外部资料整理成可供决策、写作、产品判断或战略讨论的简报。
- 需要明确哪些结论已经有来源支持,哪些仍然只是推断或待验证假设。
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、战略判断或竞品扫描。
- 时间范围、地域范围、语言范围或来源偏好。
如果研究范围过大,先收窄到一个主要问题和 3 到 5 个子问题;如果用户没有补充,就给出显式范围假设。
工具与外部事实边界
- 本 deliverable 是 tool-assisted deliverable:当宿主提供联网检索或浏览工具时,必须先检索,再输出简报。
- 最小检索应覆盖 4 到 8 个高相关来源,优先官方文档、论文、项目仓库、公司公告、权威机构、可靠媒体和可追溯的一手材料。
- 输出必须列出来源链接、发布日期或访问日期、来源类型、可信度限制和信息缺口。
- 如果宿主不提供联网检索或浏览工具,不能输出研究结论;只能输出待检索问题、推荐来源类型和降级版调研计划,并建议改用
cogx-research-plan。 - 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
cogx-research-plan:当问题仍需先拆成假设、信息源和验证路径时使用。cogt-science:定义假设、证据、反证条件和结论强度。cogm-critical-thinking:检查证据质量、替代解释和推断边界。cogm-structured-problem-solving:拆研究问题、子问题和优先验证路径。cogp-bayes:判断证据如何更新信念,避免把单一来源当成确定结论。cogp-shannon:压缩信息噪声,保留决策需要的信号。
方法
- 重述研究问题、用途、范围和成功标准。
- 判断必须检索的外部事实类型,并列出检索关键词或来源路径。
- 如果宿主有检索或浏览工具,先做最小检索;优先读取一手来源和可追溯材料。
- 将来源分为一手材料、官方文档、研究/论文、社区/媒体、市场信号和低可信线索。
- 提炼关键发现,并为每条发现标注支持来源、证据强度、反对证据或不确定性。
- 输出研究简报、分歧点、待验证清单和下一步行动。
输出契约
研究标题:
研究用途:
范围与时间:
检索过程:
来源清单:
关键发现:
证据强度:
主要分歧:
仍不确定:
对当前问题的含义:
建议下一步:
不应过度解读:
失败模式
- 没有检索就直接给研究结论。
- 只列链接,不提炼发现、证据强度和分歧。
- 把媒体转述、社区观点或搜索热度当成一手证据。
- 只找支持结论的材料,不寻找反证或替代解释。
- 引用来源但不说明日期、范围和可信度限制。
验证逻辑
- 每条关键发现必须能追溯到至少一个来源,或明确标为推断。
- 必须区分一手事实、二手解释、市场信号和作者判断。
- 必须说明检索范围、访问日期或发布日期,以及没有覆盖的范围。
- 必须给出“仍不确定”和“不应过度解读”,避免把快速调研伪装成完整研究。
边界测试
输入:
研究 Agent Skills 生态,判断 ArchSight Cognition 应该优先补脚本、eval、市场分发,还是继续扩充 SKILL.md 内容。
期望改善:
输出应先检索 Agent Skills 标准、Anthropic skills、Fabric、SuperClaude、LangChain DeepAgents 和 marketplace 资料,再区分事实、推断和建议,给出可复核来源和下一步验证。
交接
- 交给
cogx-decision-memo把研究发现转成正式决策备忘录。 - 交给
cogx-strategy-brief把研究发现压缩为战略方向和最小行动。 - 交给
cogt-product把研究发现转成产品定位、目标用户和最小验证。 - 交给
cogx-research-plan为未覆盖问题设计后续调研。
护栏
- 不要在没有联网工具时声称已经完成检索。
- 不要伪造来源、发布日期、访问日期、数据或引用。
- 不要把快速调研说成完整竞品审计、系统综述或专业尽调。
- 不要把单一来源或搜索热度当成真实需求。
- 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
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.
- 9d ago First seen · 111 lines · 45 tokens per session scan A 8847382273b1
cogx-research-brief is a skill published in the GitHub repository ArchSightLabs/archsight-cognition (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,366 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.