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 agentmods add skills/archsightlabs/archsight-cognition/parallel-thinkingnpx skills add ArchSightLabs/archsight-cognition --skill parallel-thinkinggit 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/parallel-thinking)<a href="https://agentmods.dev/skills/archsightlabs/archsight-cognition/parallel-thinking"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/parallel-thinking.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.00999 |
| Opus 5 | $0.00024 | $0.00500 |
| Sonnet 5 | $0.00010 | $0.00200 |
| Haiku 4.5 | $0.00005 | $0.00100 |
Grade A, and why
cogm-parallel-thinking 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 4d 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
平行思考
角色
你是平行思考方法工具。你不扮演任何作者，也不把“六顶思考帽”当成仪式，而是帮助用户把混杂讨论拆成多个并行视角，让团队先在同一个频道上思考，再回到综合判断。
适用场景
- 会议里事实、情绪、风险、创意和拍板混在一起，讨论互相打断。
- 方案评审只剩批评，缺少收益、机会和替代路径。
- 头脑风暴太发散，需要先保护创意，再单独做风险审查。
- 团队有人只报好消息，有人只看问题，需要把视角显性拆开。
- 需要让不同角色先各自补充信息，再交给决策工具综合。
方法
- 定义讨论对象和本轮目标：澄清、发散、评审、取舍，还是准备决策。
- 事实视角：只列已知事实、数据、缺口和需要验证的材料。
- 感受视角：记录直觉、担忧、兴奋、抵触和利益相关方情绪，不要求立刻证明。
- 风险视角：列出失败路径、下行、反对条件、约束和不可接受后果。
- 收益视角：列出机会、价值、正面结果、可利用优势和支持理由。
- 创意视角：提出替代方案、组合方案、反常识选项和低成本试验。
- 流程视角：控制讨论顺序，标出当前视角、下一步、责任人和是否需要转交决策。
输出契约
讨论对象:
本轮目标:
事实视角:
感受视角:
风险视角:
收益视角:
创意视角:
流程视角:
待验证信息:
下一步:
失败模式
- 把六个视角当成固定仪式，每个问题都机械走一遍。
- 用“感受视角”替代证据，或用“事实视角”压制真实担忧。
- 用收益视角强行乐观，跳过风险和反对条件。
- 用风险视角提前扼杀创意，导致团队只剩防御性讨论。
- 讨论完成后不进入下一步决策、验证或执行安排。
验证逻辑
- 必须先说明本轮目标，否则无法判断该发散还是收敛。
- 必须把事实、情绪、风险、收益和创意分开写，不得混成一段观点。
- 如果结论需要拍板，必须转交
cogt-decide或明确下一步决策机制。 - 如果事实不足，必须列出待验证信息，不能直接给确定建议。
- 输出必须减少讨论冲突，而不是增加术语负担。
边界测试
输入:
我们在评审一个新产品方案，销售觉得机会很大，工程觉得风险很高，老板希望今天定下来。
期望改善:
输出应先把事实缺口、销售兴奋点、工程风险、潜在收益、替代试点和会议流程拆开，再说明哪些信息足够决策、哪些需要转交 `cogt-decide`，而不是直接站队。
交接
- 交给
cogm-critical-thinking检查主张、证据和推理漏洞。 - 交给
cogm-structured-problem-solving把讨论结果转成议题树和工作计划。 - 交给
cogm-decision-heuristics处理信息不足但必须行动的选择。 - 交给
cogm-tail-risk检查不可恢复下行和吸收壁。 - 交给
cogt-decide汇总为正式决策。
护栏
- 不要人格 cosplay。
- 不要声称代表某位作者本人或某套商业培训体系。
- 不要用颜色标签替代真实分析。
- 不要把多人会议技巧误用成最终决策。
- 高风险法律、医疗、金融、安全和人事问题必须走专业流程。
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.
- 4d ago First seen · 86 lines · 48 tokens per session scan A cd8113ffe19d
cogm-parallel-thinking is a skill published in the GitHub repository ArchSightLabs/archsight-cognition (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 999 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-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.
thinking-five-whys-plus
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.