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/zhu1090093659/spec_driven_develop/deep-discussnpx skills add zhu1090093659/spec_driven_develop --skill deep-discussgit clone --depth 1 https://github.com/zhu1090093659/spec_driven_developWrote 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/zhu1090093659/spec_driven_develop/deep-discuss)<a href="https://agentmods.dev/skills/zhu1090093659/spec_driven_develop/deep-discuss"><img src="https://agentmods.dev/badge/skills/zhu1090093659/spec_driven_develop/deep-discuss.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 5.1 | $0.00181 | $0.01084 |
| Opus 5 | $0.00090 | $0.00542 |
| Sonnet 5 | $0.00036 | $0.00217 |
| Haiku 4.5 | $0.00018 | $0.00108 |
Grade A, and why
deep-discuss 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 6d 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
Deep Discuss — 结构化深度讨论
你正在执行 Deep Discuss 工作流:不急于给答案,先把问题想透。用户描述的"问题"和真正的问题之间常有鸿沟——这个流程用分阶段的纪律保证讨论的质量和深度。
通用规则
- 标注阶段:每次回复开头标注当前阶段(如
Phase 2 → 问题审查;转换时Phase 2 done → Phase 3:深度分析),回复末尾简要说明下一步。 - 不要跳阶段:至少过一遍 Phase 1-4;Phase 5/6 可按问题复杂度合并,但不能完全跳过。用户中途提供新信息时,评估是否回到更早阶段。
- 信息不足即停:Phase 2 发现信息不足时,先问再等,不要带着未验证的假设往下走。
- 直接坦诚:用户判断有误就直说并给理由;不确定的事用置信度表述,不用模棱两可的"可能"。
Phase 1:接收信息
只接收,不分析。完整理解用户提供的全部信息(文字、截图、用户的初步判断),用自己的话复述关键点(≤3-5 句)确认理解无误。描述明显模糊时,复述后只提 1-2 个最关键的澄清问题。
Phase 2:问题审查(质量门控)
三层审查:
- 问题是否成立:现象是否真构成问题?用户归因是否合理?有无需验证的前提假设?
- 信息是否充足:缺什么关键信息(标注:必须有 / 最好有 / 锦上添花)?信息不足时明确说明"能分析到什么程度,还差什么",然后暂停等用户补充。
- 是否有隐藏问题:用户没注意到的其他问题?表面现象之下有无更深根因?
建议输出格式(可灵活调整):
## Phase 2:问题审查
### 问题成立性
[判断 + 理由]
### 信息充足度
[已有信息 / 缺失信息 / 对分析的影响]
### 潜在隐藏问题
[发现 / 或"暂未发现"]
Phase 3:深度分析
信息确认足够后展开分析:全面(考虑多种可能性)、有深度(追到 root cause)、有层次(分维度而非线性罗列)、诚实(标注置信度)。总结核心发现后等待用户反馈:补充信息 → 回 Phase 2;认可 → 进 Phase 4;有分歧 → 讨论并调整。
Phase 4:方案设计
- 优先给 2-3 个可选方案(除非只有唯一合理解法)。
- 每个方案明确:做什么、为什么、代价、适用场景;方案间有 trade-off 要明确对比。
- 给出推荐方案及理由,最终选择权留给用户。
Phase 5:方案自检
主动自查:遗漏的场景或边界条件?前提假设是否都成立?复杂度是否被低估?有无更简单的替代?是否覆盖了 Phase 2 识别的所有问题(含隐藏问题)?发现问题当场修正。
Phase 6:最终确认
用户确认方向后做最后一轮检查:步骤完整性、意外情况预案、执行后如何验证问题真解决了、补充建议。目标是从"可以做"提升到"做得好"。
Phase 7:执行(可选)
仅在用户明确说"开始执行"等指令时进入。按确认的方案逐步执行,每个关键步骤简要汇报,遇意外暂停并回到讨论模式。
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.
- 6d ago First seen · 68 lines · 181 tokens per session scan A 9c3fdfed1fde
deep-discuss is a skill published in the GitHub repository zhu1090093659/spec_driven_develop (978 stars, last pushed 1mo ago), licensed MIT. It adds 181 tokens to every session and 1,084 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
build-executor
Govern implementation from an approved execution contract. Invoke when execution-contract.md is approved and the user wants disciplined build work, TDD execution, or guarded batch-by-batch implementation.
workflow-start
Primary entry point for the spec-superflow state-machine workflow. Invoke when the user is inside an active spec-superflow change directory (look for .spec-superflow.yaml, changes/ /, proposal.md, specs/, design.md, tasks.md, or execution-contract.md) and asks to start, continue, resume, implement, plan, or figure out…
release-archivist
Close out a spec-superflow change with verification, summary, and archive readiness. Invoke when implementation is complete, verification is underway, or the user asks for a final wrap-up.
bug-investigator
Use when encountering any bug, test failure, or unexpected behavior during spec-superflow execution, before proposing fixes. Invoked automatically when build-executor hits a blockage.
contract-builder
Convert approved planning artifacts into an execution contract. Invoke when the user wants to start building, asks to move from planning to implementation, or when execution-contract.md is missing or stale.
spec-writer
Create or refine spec-superflow planning artifacts. Invoke when the change is understood well enough to write proposal.md, specs/, design.md, and tasks.md.