A reporting workflow that turns a long, complex analysis into an interactive HTML briefing for a decision-maker. It organizes conclusions, evidence, comparisons, and visual explanations around a specific decision.

Use it when someone needs to compare options, inspect evidence, change assumptions, give feedback, or make a decision from existing analysis.

It reduces the effort needed to understand tangled information and makes important differences or trade-offs easier to examine before choosing.

brief-me — Skill for Codex by jinhanbuilds

Install

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.

Any agent

npx skills add jinhanbuilds/brief-me --skill brief-me

Clone the repo

git clone --depth 1 https://github.com/jinhanbuilds/brief-me

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jinhanbuilds/brief-me/brief-me/github.svg)](https://agentmods.dev/skills/jinhanbuilds/brief-me/brief-me)

Your own site

<a href="https://agentmods.dev/skills/jinhanbuilds/brief-me/brief-me"><img src="https://agentmods.dev/badge/skills/jinhanbuilds/brief-me/brief-me/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jinhanbuilds/brief-me/brief-me"><img src="https://agentmods.dev/badge/skills/jinhanbuilds/brief-me/brief-me.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,336 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00076	$0.01336
Opus 5.5	$0.00030	$0.00534
Sonnet 5.5	$0.00015	$0.00267
Haiku 4.5	$0.00008	$0.00134

Measured 1mo ago against content hash 090ea310c798, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

brief-me 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 1mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (evals/fixtures/scripts/check-briefing.mjs, evals/fixtures/scripts/check-condition.mjs, evals/fixtures/scripts/check-structure.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/brief-me/SKILL.md · 54 lines

What it actually says

Brief Me

让 AI 先组织好复杂度，再回来汇报。用户应当顺着一条清楚的主线看懂局面、看见关键关系，并在理解之后方便地表达判断。

成功是一段连续的体验：知道要判断什么 → 看懂理由与关系 → 追问必要依据 → 表达自己的意见 → 带着反馈继续对话。 页面形式由当前任务决定。

先形成可以讲给人听的判断

从已有材料恢复受众、当前问题、约束和本次希望获得的回应。只追问会实质改变交付且无法从材料恢复的缺口。材料杂乱或判断任务隐含时，读取 decision-context.md；这些背景用于内部理解。

在画页面或列组件前，先用连贯的自然语言把事情讲通：发生了什么，为什么影响当前判断，材料支持怎样的建议或取舍，还有什么条件会改变它。用户要自行判断时，以关键差异为主线；需要建议时，给出建议与成立条件。

这段综合是 Agent 的工作底稿，足够指导制作即可，不新增用户审批步骤。检查理由是否真正支持主张、建议是否回应发现。一个响亮标题加一串分类标签，还没有完成综合。

把主线变成可见、可回应的体验

设计时读取 briefing-design.md，其中包含两组虚构材料的正反示例。根据当前问题选择阅读路径、视觉和用户动作，再选择所需的前端、可视化或其他辅助能力；不固定依赖外部 Skill。

保持判断的完整性。 围绕当前问题连接发现、证据、影响和回应。标题、短段、图与必要对照各司其职；把内部分析字段留在后台，让读者能连续理解论证。
把关键关系画出来。 用空间、连接、尺度、对齐或变化表达至少一项决定性关系。层级帮助找到重点，图形帮助理解结构；有必要画清的依赖、因果或取舍时，排版整齐仍不够。
在理解发生的位置参与。 让用户在看过相关分析后就能比较、追问或留下判断。提供预设之外的自由意见入口，反馈能复制或导出。筛选、滑块、目标切换等只在当前任务需要时加入。
按需深入。 主阅读层保留判断所需的关键依据与限制，完整来源、历史和逐项材料按需展开。多个关联问题先交代关系，再按用户理解的顺序展开。

默认交付可直接打开、便于分享的自包含 HTML；确有需要才采用小型静态项目。保持跨宿主可用，不强制某种图表、框架、页数或组件。

保持反馈与事实一致

数字保留来源、时间、单位和口径；推断、假设和未知在影响判断的位置说明。材料不足时讲清能判断到哪里，不扩张成未经请求的研究。

只对现有数据支持的确定性逻辑进行页面内重算。条件变化后同步相关数字、结论、理由与反馈。新文字需要 AI 重新理解时，保留用户输入，标明哪些判断需要回到对话重审；页面不伪造新分析。

复制或导出的反馈保留实际发生的选择、条件、自由意见和待重审部分。默认说明“复制后粘贴回 Agent 继续讨论”；只有真实接入并验证过发送通道，才能声称已交给 AI。页面选择属于讨论反馈，执行、发送、发布和写回仍需相应授权。

用真实阅读与操作验收

打开实际页面，依次检查下列结果；修复后只复查受影响部分。

能讲通。 从首屏开始读主线，能说清本次问题、主要判断和理由。需要反复跳转栏目才能连起来时，先重组论述，再调整版式。
能看懂关系。 指出一项具体关系，以及图形如何帮助理解它。做删除测试：删去视觉后，若理解同样容易，就换一种表达或删去装饰。
能就地回应。 实际比较或追问一次，再输入预设之外的意见。确认用户不必离开相关分析很远才能回应。
能接着工作。 实际复制或导出，回读内容；确认选择、条件和自由意见完整且一致。复制受限时提供可手动复制的文本，不能假报成功。
能正常使用。 检查窄屏、键盘路径和核心状态；信息有明确阅读次序，操作可识别，减少动态效果设置得到尊重。

窄屏不是把桌面版缩小：在实际视口检查 document.documentElement.scrollWidth <= innerWidth，给网格子项和面板设置 min-width: 0，让长标签换行；路线、表格或对照内容需要横向阅读时，只让局部容器滚动，不让整页被撑宽。

结构检查、功能检查和体验判断分别说明。字段齐全、图形存在、按钮可点，只证明对应部分；整体理解仍困难时，继续修复主线、关系表达或回应位置。

交付时给出产物入口、实际走查结果及仍影响使用的限制。没有真实判断任务时直接说明不适用；不强行生成决策界面。

Files

What ships with it

11 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.

Changes

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.

1mo ago Changed · -61 lines · -45 tokens per session 090ea310c798
2mo ago First seen · 115 lines · 121 tokens per session scan A c01b454a094d

Subscribe to this mod's changes

brief-me is a skill published in the GitHub repository jinhanbuilds/brief-me (37 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 1,336 once invoked, about $0.0003 per session on Opus 5.5. 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.

Analytics and metrics Writing and docs agent-skills ai-agents codex consulting data-visualization decision-support

brief-me next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
brief-mejinhanbuilds/brief-me	Skill	37	1mo ago	MIT	A	76	Codex
strategy-consulting-visualizationkgraph57/mckinsey-style-visualization-skill	Skill	169	19d ago	MIT	A	55	Claude Code, Codex
consulting-deckzairuilab/consulting-deck	Skill	31	1mo ago	none	A	101	Codex
information-uirenfei-design/fify-plugin	Skill	1	2mo ago	Apache-2.0	A	82	Claude Code, Codex
html-ppt-zhangzara-matnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	51	Claude Code, Codex
auto-researchsickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	29	Claude Code
dashboard-designmckinsey/vizro	Skill	3.8k	yesterday	Apache-2.0	A	71	Claude Code