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/masonsre/debrief/skillnpx skills add MasonSRE/debrief --skill skillgit clone --depth 1 https://github.com/MasonSRE/debriefWrote 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/masonsre/debrief/skill)<a href="https://agentmods.dev/skills/masonsre/debrief/skill"><img src="https://agentmods.dev/badge/skills/masonsre/debrief/skill.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 | $0.00116 | $0.00877 |
| Opus 5 | $0.00058 | $0.00439 |
| Sonnet 5 | $0.00023 | $0.00175 |
| Haiku 4.5 | $0.00012 | $0.00088 |
Grade A, and why
daily-work-log 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
每日工作日报（Debrief）
基于 Debrief（debrief CLI）把本机 AI 编程活动整理成日报。CLI 只读本地日志、不联网、自动脱敏、零依赖。
流程
1. 跑 CLI 生成日报（文字 + HTML + JSON）
# 已全局安装（npm i -g debriefly）/ npx debriefly：
debrief --lang zh --out ~/work-logs
# 或从源码：
node /path/to/debrief/bin/debrief.mjs --lang zh --out ~/work-logs
- 产出
~/work-logs/debrief-<日期>.md（文字版）、.html（图片版）、.json（结构化）。 - 常用参数：
--date YYYY-MM-DD指定日期、--tz时区、--lang en|zh、--sources claude,codex,gemini,git。 - 想纳入 Hermes Agent / WorkBuddy / OpenClaw 的活动（默认不开）：加
--sources claude,codex,gemini,git,hermes,workbuddy,openclaw。三者内容都存在 SQLite，靠系统sqlite3CLI 只读读取；没装sqlite3就自动跳过。WorkBuddy 本地只存会话标题（对话正文在云端/内存），OpenClaw 汇总的是task_runs里的任务文本。 - 想直接拿文本/JSON：
debrief --html/--json打到 stdout。
2. （可选）润色 / 总结
CLI 出的是「客观汇总」。如需更像周报/standup 的叙述，基于 .json 或 .md 再加一段简短总结即可 —— 但只能基于 CLI 输出，不要臆造、不要引入采集之外的信息；任何拿不准的内容宁可不写。
3. （可选）发图 / 发消息
- 文字版：直接发文本。
- 图片版：把
.html用浏览器/无头 Chrome 截成 PNG 再发（飞书 / Slack / 企微都支持发图）。 - 两份一起发是最佳：文字便于检索，图片便于一眼看完。
定时（无人值守）场景
被 cron / Hermes 在每天固定时间（如 18:00–19:00）调用时：
- Heartbeat 守卫：若触发时刻早于约定时间，当天数据不完整 —— 不生成 / 不发送，只报告「调度异常：触发过早」。
- 已授权无人值守：不向用户请求确认 / 审批；可直接跑 CLI、写文件、发消息。
- 不自行登录任何网站、不处理或复述密码密钥、不修改任何代码仓库。
备注
- CLI 只认本机日志，必须在本机运行（云端读不到
~/.claude、~/.codex、~/.gemini）。 - 这是「汇总 / 归纳」类技能，不替代真实判断：拿不准的内容宁可留空。
- 安装/源码：
npm i -g debriefly· https://github.com//debrief
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 · 42 lines · 116 tokens per session scan A 53b81ceec043
daily-work-log is a skill published in the GitHub repository MasonSRE/debrief (3 stars, last pushed 2mo ago), licensed MIT. It adds 116 tokens to every session and 877 once invoked, about $0.0006 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
gingiris-seo-geo-agent
SEO/GEO Agent Operations SOP v2 — Rebuilt from real-world operations (analook.com 0→launch, GSC incident, DataForSEO monitoring, gingiris.tools post-migration recovery). What's new in v2: • Step-by-step onboarding (Q1→Q6), multiple choice wherever possible — no big forms • Mandatory daily SEO log — first item is…
gingiris-twitter-agent-ops
Twitter/X Agent Operations SOP v2 — Rebuilt from real dual-account operations. Real data: • CN account: grew from 1,150 → 3,679 followers (14 months), 1 tweet/day, OAuth1 direct post • EN account: Buffer API • Real incidents: cron silent-failed for 2 weeks unnoticed, analytics data off by 17×, thread performance worse…
wechat-daily-report-skill
生成微信群聊日报。优先用 jackwener/wx-cli 获取本地微信聊天记录，再输出新版日报 HTML 和 PNG，包含今日剧情、聊天气泡、资料收纳、问答、成员观察和成员过滤。.
claude-daily
Use when the user wants a daily report, session card, work recap, AI coding activity summary, or PRD-compliant Compound Daily ingestion payload covering local AI coding sessions (Claude Code + Codex CLI). The skill drives the full 6-step pipeline (prepare → generate → emit → upload) end-to-end inside a single Claude…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.