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 charlie947/life-automation-skills --skill research-briefgit clone --depth 1 https://github.com/charlie947/life-automation-skillsWrote 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/charlie947/life-automation-skills/research-brief)<a href="https://agentmods.dev/skills/charlie947/life-automation-skills/research-brief"><img src="https://agentmods.dev/badge/skills/charlie947/life-automation-skills/research-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/charlie947/life-automation-skills/research-brief"><img src="https://agentmods.dev/badge/skills/charlie947/life-automation-skills/research-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00130 | $0.01899 |
| Opus 5.5 | $0.00052 | $0.00760 |
| Sonnet 5.5 | $0.00026 | $0.00380 |
| Haiku 4.5 | $0.00013 | $0.00190 |
Grade A, and why
research-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 2mo 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use this skill
Use it when the user wants a short, decision-useful brief they can trust, not a wall of links:
- "Research [topic]" / "brief me on [person or company]" / "background on this vendor before the call"
- "What's the latest on [X]?" / "state of play on [Y]?" / "catch me up on [Z]"
- "Build me a research brief and file it in Notion / Drive"
- Any request for a sourced, filed rundown ahead of a meeting, decision, pitch, or post.
This is the light, business-brief version of research. It is fast (a handful of searches, minutes not hours), it fits on a page, and it ends up filed where the user already works. If the user wants an exhaustive multi-hour investigation or an academic paper with dozens of sources, that is a different, heavier job, say so and offer this instead.
Do not use it to state anything you have not verified as fact, to file without the user's confirmation, or to research private individuals using non-public data.
What it needs (setup)
A built-in tool plus one filing connector:
- Built-in web search + fetch (a tool, not an OAuth connector), to find sources and open them. This is the engine of the brief.
- One filing destination (login-only OAuth, no build), whichever the user already uses:
- Google Drive connector, create the brief as a document.
- Notion connector, create the brief as a page (the user names the parent page or database).
If web search is not available, stop and say so, do not answer a research question from memory alone. If neither Drive nor Notion is connected, still deliver the brief in chat and offer to file it once one is enabled.
Be honest about the limits:
- A search result appearing is not the same as a source being read. Search returns titles, snippets, and links. The actual page can be paywalled, blocked, or fail to load. You have only read a source once you have fetched and opened it.
- Web search has a recency and region boundary. It will not surface everything, and very recent events may be thin or contradictory. Say when the trail is thin rather than filling the gap.
- The filing connector writes a document or page, but it does not control who can see it. Do not claim a brief is "shared" or "private", just report where it was filed and let the user set access.
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.
- 2mo ago First seen · 92 lines · 130 tokens per session scan A 36057d048ec5
research-brief is a skill published in the GitHub repository charlie947/life-automation-skills (34 stars, last pushed 2mo ago), licensed MIT. It adds 130 tokens to every session and 1,899 once invoked, about $0.0005 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.
research-brief compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| research-briefcharlie947/life-automation-skills | Skill | 34 | 2mo ago | MIT | A | 130 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |