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 OneWave-AI/open-agent-stack --skill daily-ai-briefgit clone --depth 1 https://github.com/OneWave-AI/open-agent-stackWrote 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/onewave-ai/open-agent-stack/daily-ai-brief)<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/daily-ai-brief"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/daily-ai-brief/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.
<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/daily-ai-brief"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/daily-ai-brief.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00067 | $0.00488 |
| Opus 5 | $0.00034 | $0.00244 |
| Sonnet 5 | $0.00013 | $0.00098 |
| Haiku 4.5 | $0.00007 | $0.00049 |
Grade A, and why
daily-ai-brief 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 9d 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
Daily AI Brief
Produce a ranked AI-news briefing by running three roles in sequence: scout (sweep), analyst (rank), editor (write). This skill needs the web — use the built-in web search and fetch tools. No API key is required.
Workflow
- Set scope. Default to the last 24 hours on weekdays and the last 7 days on Mondays. Honor any window, vertical, or format the user specifies instead.
- Load the source list from
references/sources.mdand the reader's declared stack from project context (CLAUDE.md or the request). - Scout: run web searches across the source groups in priority order — model releases and first-party vendor posts first, then high-cadence feeds, digests, deep dives, and community signal. Collect title, source, date, and link for each candidate.
- Analyst: dedupe items that report the same event, drop anything outside the scope window, and corroborate community buzz against a primary source before keeping it. Discard items you cannot verify.
- Analyst: rank by signal. Weight model releases and first-party announcements highest. Flag every item that touches the reader's stack.
- Editor: write the briefing. Lead with the top item. For each entry give a headline, a one-line why-it-matters, the source link, and a "touches your stack" tag when it applies.
- Cap the briefing at the most significant items (default 5 to 8). Note anything notable that was cut so nothing important is silently dropped.
- Close with the scope window covered and the next scheduled run so the cadence stays clear.
Rules
- Cite a working source link for every claim. Never assert a release or benchmark without a source.
- Prefer primary sources over aggregators when both cover the same item.
- Keep entries tight. The reader wants signal, not recap.
References
references/sources.md— the full researched source list grouped by job, with ranking guidance.
What ships with it
1 file 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.
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.
- 9d ago First seen · 30 lines · 67 tokens per session scan A 38a69987edef
daily-ai-brief is a skill published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 29d ago), licensed MIT. It adds 67 tokens to every session and 488 once invoked, about $0.0003 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
guidance
Constrain LLM output with grammars; guarantee valid JSON.
outlines
Outlines: structured JSON/regex/Pydantic LLM generation.
instructor
Structured LLM outputs validated with Pydantic.
obliteratus
OBLITERATUS: abliterate LLM refusals (diff-in-means).
dspy
DSPy: declarative LM programs, auto-optimize prompts, RAG.
saelens
Train sparse autoencoders to interpret model features.