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 hashgraph-online/awesome-codex-plugins --skill discuss-phasegit clone --depth 1 https://github.com/hashgraph-online/awesome-codex-pluginsWrote 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/hashgraph-online/awesome-codex-plugins/discuss-phase)<a href="https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/discuss-phase"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/discuss-phase.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.01015 |
| Opus 5 | $0.00036 | $0.00508 |
| Sonnet 5 | $0.00014 | $0.00203 |
| Haiku 4.5 | $0.00007 | $0.00102 |
Grade A, and why
discuss-phase 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 3d 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
Discuss Phase
用途
- 把"需求文字看起来清楚了就开干"改成"先把灰色地带和隐含假设摊开讨论"。
- 适合需求有模糊空间、存在多种可行路线、或用户偏好尚未表达的场景。
- 在
/team-intake完成后、/team-plan之前推荐触发。
两种模式
discuss(交互质疑模式)
逐项质疑需求中的灰色地带,引导用户做出偏好选择。适用于用户在场、可以即时回答的场景。
assumptions(代码分析优先模式)
先扫描代码库识别现有模式和约束,把代码中已有的事实作为假设基础,仅对代码无法回答的灰色地带提问。适用于代码库已有大量存量逻辑的迭代场景。
默认做法
-
收集输入:读取
/team-intake的产出(PRD、需求简报),提取目标、范围、约束和待确认项。 -
识别灰色地带:按以下维度自动扫描未锁定的决策点:
- UI 交互:状态管理方式、加载/空/错误态策略、动效取舍
- API/数据:分页策略、错误码规范、缓存策略、数据保留周期
- 架构:同步/异步、推/拉、单体/微服务边界
- 业务规则:边界条件处理、权限粒度、审批流程节点
- 质量:性能预算、浏览器兼容基线、可访问性等级
- 部署:环境策略、Feature Flag、灰度比例
-
Forcing Questions(来自 gstack office-hours 方法论):
- 如果这个功能只能做一件事,那件事是什么?
- 这个功能的用户是谁?他们当前的替代方案是什么?
- 半年后回看,什么情况下我们会认为这是浪费时间?
- 最小可交付版本是什么?跟完整版的差距在哪?
- 有哪些假设一旦不成立,方案就会完全不同?
- 哪个决策如果做错了代价最大?
-
逐项讨论:每个灰色地带呈现为:
- 背景:为什么这是一个需要讨论的点
- 选项:可行方案列表,每个带利弊分析
- 推荐:基于代码分析和最佳实践的建议
- 等待用户确认或修改
-
产出 CONTEXT.md:将所有讨论结论写入
docs/artifacts/{slug}/context.md,包含:- 确认的技术偏好和约束
- 灰色地带的最终决策
- 待进一步验证的假设(标记为
[ASSUMPTION]) - 明确排除的选项及排除原因
触发信号
/team-intake产出中包含 3 个以上待确认项。- 需求涉及新领域或新技术栈,团队缺乏先验经验。
- 存在多个合理的技术路线,无法在 intake 阶段直接锁定。
- 需求涉及跨团队或跨系统边界。
- 用户显式要求"先讨论一下再开始"。
配套约束
- 不替代 intake:discuss-phase 消费 intake 的输出,不重新做需求收集。
- 不替代 plan:discuss-phase 产出偏好和约束,不产出任务拆解和排期。
- 时间控制:单次 discuss 控制在 6-10 个灰色地带以内,超出时建议分批或升级给
architect。 - 结论必须落盘:所有讨论结论写入
context.md,不停留在对话上下文中。 - assumptions 模式红线:代码分析得出的假设必须标注证据来源(文件路径 + 行号),不能凭直觉编造。
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.
- 3d ago First seen · 74 lines · 71 tokens per session scan A 89f12bd42b35
discuss-phase is a skill published in the GitHub repository hashgraph-online/awesome-codex-plugins (956 stars, last pushed today), licensed Apache-2.0. It adds 71 tokens to every session and 1,015 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
search
Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.
sprr
Single PR reviewer for awesome-quant. Use when the user asks to review, validate, comment on, label, close, or merge one specific pull request that adds README.md entries. Triggers include "sprr", "review PR", "check PR", and "validate contribution".
bprr
Bulk PR reviewer for awesome-quant. Use when the user asks to review all open PRs, review unreviewed PRs, bulk review, or mentions "bprr". Reviews open PRs lacking the reviewed label and presents a summary before any merge/comment/label action.
drawio-reconstruction
Reconstructs reference images into high-fidelity, editable Draw.io files with rendered previews: native Draw.io elements carry text and structure, SVG covers simple icons that match the reference, and cropped or transparent PNGs preserve complex visuals. Use when the user wants a diagram image, research figure…
benchmark-paper-template
Structures Benchmark and Evaluation papers using the five-pillar framework (Research Gap, Construction Pipeline, Evaluation Framework, Empirical Findings, optional Companion Method). Returns a completeness audit, a six-part Introduction logic chain, a Section 2-7 skeleton, and a pre-submission checklist. Use when…
reverse-engineering-android-malware-with-jadx
Reverse engineers malicious Android APK files using JADX decompiler to analyze Java/Kotlin source code, identify malicious functionality including data theft, C2 communication, privilege escalation, and overlay attacks. Examines manifest permissions, receivers, services, and native libraries. Activates for requests…