daily-brief-bot

daily-brief-bot is a skill for Claude Code from bam-bam-2/solo-skills. It costs 58 tokens per session (2,558 once invoked), scanned A, original, MIT.

A daily bot that collects new articles, selects three related to the user's current interests, summarizes them, and sends them in a Discord direct message. Discord is a chat service.

In plain words
What is it for?
Use it to collect articles, compare them with notes and saved skills, send a daily brief, verify its links, and save selected items to a knowledge vault.
Why use it?
It turns a large stream of new writing into a short, scheduled reading brief connected to the user's ongoing work.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the solo-skills plugin — 26 skills shipped together

Good fit Use it to collect articles, compare them with notes and saved skills, send a daily brief, verify its links, and save selected items to a knowledge vault.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bam-bam-2/solo-skills/daily-brief-bot
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 bam-bam-2/solo-skills --skill daily-brief-bot
Clone the repo
git clone --depth 1 https://github.com/bam-bam-2/solo-skills

Made for: Claude Code.

Or install solo-skills, the plugin that ships this one along with the rest of its 26 skills.

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.

agentmods badge for daily-brief-bot

README.md
[![agentmods](https://agentmods.dev/badge/skills/bam-bam-2/solo-skills/daily-brief-bot/github.svg)](https://agentmods.dev/skills/bam-bam-2/solo-skills/daily-brief-bot)
Your own site
<a href="https://agentmods.dev/skills/bam-bam-2/solo-skills/daily-brief-bot"><img src="https://agentmods.dev/badge/skills/bam-bam-2/solo-skills/daily-brief-bot/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.

agentmods 80×15 button for daily-brief-bot

Your own site · 80×15
<a href="https://agentmods.dev/skills/bam-bam-2/solo-skills/daily-brief-bot"><img src="https://agentmods.dev/badge/skills/bam-bam-2/solo-skills/daily-brief-bot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,558 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 35
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 70
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 129
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Rogue Agent · line 65
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.02558
Opus 5 $0.00029 $0.01279
Sonnet 5 $0.00012 $0.00512
Haiku 4.5 $0.00006 $0.00256

Measured 12d ago against content hash 85184e694f2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

daily-brief-bot scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

import os,json,base64,urllib.request
skills/daily-brief-bot/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

데일리 브리프봇

사용자는 매일 아침 10시에 디스코드 DM으로 데일리 브리프봇 아티클을 받는다. 지피터스(gpters.org) 신규 글을 전부 읽고, 사용자의 제2두뇌 볼트·에이사이드 스킬/메모리와 대조해 사용자가 지금 붙들고 있는 고민에 닿는 3건을 골라 편지 형식으로 보낸다. 각 항목에 번호(1~3)와 원문 링크가 붙어 있다.

"여백"은 이 봇이 후보를 고르는 내부 판정 기준을 부르는 말이다(볼트에 한 번도 안 나온 것). 사용자에게 말할 때는 봇 이름인 데일리 브리프봇으로 부른다.

트리거

  • "데일리 브리프봇 고치자" — 톤·길이·건수·시간 등 편집. 아래 편집 표 참고
  • "데일리 브리프봇 2번 해보자" / "8/13 2번 해보자" / "어제 그거 해보자" — 실행
  • "오늘 데일리 브리프봇 뭐 왔어" — 읽어주기만
  • "이거 볼트에 넣어" — 볼트 승격
  • 옛 호칭 "여백 브리핑"으로 불러도 같은 것을 가리킨다

인프라 위치 (전부 원격 머신, ssh remote-host)

~/Projects/<프로젝트>/
  prompt-template.md  ★ 톤·형식·길이·몇 건을 결정하는 유일한 파일. 편집은 거의 여기만 고친다
  collect.mjs   지피터스 신규 글 수집 (Bettermode GraphQL, 게스트 토큰 · 로그인 불필요)
  brief.mjs     볼트·스킬·메모리 대조 → 후보 22건 추린 뒤 템플릿에 끼워 프롬프트 생성
  verify.mjs    브리핑 링크가 실제 수집분인지 대조·정정
  dm.py         디스코드 DM 발송 (stdin → 사용자 DM, 1900자씩 분할)
  capture.py    사용자의 DM 답장 회수 (10분마다)
  run.sh        매일 10:00 전체 실행 (launchd com.bambam.gpters-brief)
  .env          DISCORD_TOKEN / BAMBAM_USER_ID / CLAUDE_CODE_OAUTH_TOKEN (600)
  ctx/          맥북에서 동기화한 에이사이드 skills/ · memory/ ("이미 하고 있는 것" 판정용)
  state/
    posts-YYYY-MM-DD.json   그날 수집한 글 전문
    brief-YYYY-MM-DD.md     그날 보낸 아티클
    marks.jsonl             사용자가 DM에서 표시한 관심 항목
    done.jsonl              실제로 실현한 항목 (재제안 금지 목록)

사용자 볼트: ~/Library/Mobile Documents/com~apple~CloudDocs/제2두뇌 (원격 머신에서도 접근됨)

현재 확정된 형식 (2026-08-13 사용자 승인)

  • 아티클이다. 목록이나 알림이 아니다. 링크를 하나도 안 눌러도 내용을 다 알 수 있어야 한다.
  • 문체는 "사용자님" + 해요체의 편지. 관찰 보고서 금지.
  • 첫 문단은 반드시 "요즘 ~에 걸려 계신 것 같아요" 로 시작해 고민을 한 가지로 짚는다. 노트 제목 나열 금지. 틀려도 좋으니 구체적으로 짚는다.
  • 3건, 전체 1만자 안팛. 앞 2건은 짚은 고민에 바로 닿는 것, 마지막 1건은 안 해본 것.
  • 각 항목: 그 사람 상황 → 무엇을 어떻게 했는지(도구·프롬프트·숫자 그대로) → 결과 → 사용자님 쪽이랑 겹치는 데(볼트·스킬 근거) → "이거 한번 시도해보시면 어때요?" → 오늘 30분 → 원문 링크

편집 요청 처리

사용자가 "데일리 브리프봇 고치자" 계열로 말하면 아래에서 해당하는 파일만 고친다.

요청 고칠 곳
톤, 문체, 형식, 길이, 몇 건, 어떤 순서로, 금지 표현 prompt-template.md ← 거의 전부 여기
어떤 글을 후보로 올릴지 (점수 기준, 후보 개수, 활동 판정 기간 7일) brief.mjs
어떤 카테고리를 수집할지, 몇 건 가져올지 collect.mjs
보내는 시각 ~/Library/LaunchAgents/com.bambam.gpters-brief.plist → 수정 후 unload/load
모델 (클로드 → 코덱스 폴백) run.sh

Read the full file on GitHub · 143 lines

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.

  1. 12d ago First seen · 143 lines · 58 tokens per session scan A 85184e694f2a

Subscribe to this mod's changes

daily-brief-bot is a skill published in the GitHub repository bam-bam-2/solo-skills (363 stars, last pushed 9d ago), licensed MIT. It adds 58 tokens to every session and 2,558 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.