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 commands/leiting-eric/dailybrief/run-dailygit clone --depth 1 https://github.com/leiting-eric/DailyBriefWrote 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/commands/leiting-eric/dailybrief/run-daily)<a href="https://agentmods.dev/commands/leiting-eric/dailybrief/run-daily"><img src="https://agentmods.dev/badge/commands/leiting-eric/dailybrief/run-daily.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 | $0.00015 | $0.00806 |
| Opus 5 | $0.00008 | $0.00403 |
| Sonnet 5 | $0.00003 | $0.00161 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
run-daily scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the daily digest right now. Don't ask for confirmation — the user explicitly invoked this.
Step 0: locate the project root (cross-platform, works from any cwd)
Read the path from ~/.daily-brief-config (written by install.mjs). Use a small Node one-liner so it works on Windows / macOS / Linux:
node -e "const fs=require('fs'),os=require('os'),path=require('path');const cfg=path.join(os.homedir(),'.daily-brief-config');if(fs.existsSync(cfg)){process.chdir(fs.readFileSync(cfg,'utf8').trim());console.log(process.cwd())}else if(fs.existsSync('package.json')){console.log(process.cwd())}else{console.error('daily-brief not installed. Run bootstrap or: node scripts/install.mjs --global');process.exit(1)}"
That command prints the resolved project root. cd into it before running anything else:
- Windows PowerShell:
Set-Location (node -e "...") - bash / zsh:
cd "$(node -e '...')"
If the Node check exits non-zero, the user hasn't installed yet — tell them to run the bootstrap or node scripts/install.mjs --global manually.
Step 1: trigger the scheduled task (platform-specific)
Windows:
Start-ScheduledTask -TaskName DailyBrief
Start-Sleep -Seconds 3
Get-ScheduledTaskInfo -TaskName DailyBrief | Format-List LastRunTime, LastTaskResult
Confirm LastTaskResult = 267009 (running).
macOS:
launchctl start com.daily-brief
# Status: launchctl list | grep daily-brief
Linux (cron, no manual trigger — just run the wrapper directly):
node scripts/run-daily.mjs &
If "task not found" / "could not find specified service": user hasn't run the installer. Tell them to run node scripts/install.mjs --global.
Step 2: monitor in background
The daily run produces logs/daily-<YYYY-MM-DD>.log (local date). Tail it as it grows:
# Polling approach (works any platform):
node -e "const fs=require('fs');const f='logs/daily-'+new Date().toISOString().slice(0,10)+'.log';let prev=0;const t=setInterval(()=>{if(fs.existsSync(f)){const s=fs.readFileSync(f,'utf8');if(s.includes('] OK')){console.log('DONE OK');clearInterval(t)}else if(s.match(/]\sFAILED/)){console.log('DONE FAILED');clearInterval(t)}}},30000)"
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 · 71 lines · 15 tokens per session scan A 4fa7c8a5d6a6
run-daily is a command published in the GitHub repository leiting-eric/DailyBrief (345 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 806 once invoked, about $0.0001 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 commands, from other repositories
company
Brief the CEO: routes a mission across 8 departments (50 employees) and returns a Board Memo.
onboard
Configure an optional active team profile in three short questions.
standup
Daily standup: all 8 departments report on the current project in parallel.
evolve
Analyze instincts and suggest or generate evolved structures.
replay
Summarize one Agent Monitor session by id — header plus a concise transcript recap.
firm
Convene your standing AI staff — memos on every beat, a board session without you, minutes with dissent preserved.