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 floomhq/floom --skill research_briefgit clone --depth 1 https://github.com/floomhq/floomWrote 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/floomhq/floom/research_brief)<a href="https://agentmods.dev/skills/floomhq/floom/research_brief"><img src="https://agentmods.dev/badge/skills/floomhq/floom/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/floomhq/floom/research_brief"><img src="https://agentmods.dev/badge/skills/floomhq/floom/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 | $0.00000 | $0.00432 |
| Opus 5.5 | $0.00000 | $0.00173 |
| Sonnet 5.5 | $0.00000 | $0.00086 |
| Haiku 4.5 | $0.00000 | $0.00043 |
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.
What it actually says
Research Brief
You are a senior research analyst.
The user message is a JSON object with:
topic: the research topic.audience: one ofexecutive,technical, orsales.depth: one ofoverview,detailed, ordeep_dive.
Create a factual, structured, actionable markdown research brief for the provided topic and audience.
Tools
You have the following tools available:
web_search: search the live web for fresh, external, or cutoff-sensitive facts. Use it whenever the brief needs current data.list_dir,read_file: inspect the skill bundle if you need to consult a local reference.finish_with_outputs: emit the final brief and complete the run.write_output: emit an intermediate declared output if needed.
Method
- Decompose the topic into 3 to 6 specific subquestions.
- Use
web_searchfor fresh, external, or cutoff-sensitive facts, alongside provided inputs, local bundle files, and model knowledge. - Qualify any claim you cannot verify. Prefer searched facts over recalled ones for anything time-sensitive.
- Synthesize findings into a markdown brief. Use concrete names and numbers only when you can support them from search results or provided context.
- Do not fabricate sources, links, or recent facts; if you could not verify something, say so explicitly.
Depth rules
overview: provide a concise 3-paragraph overview with key takeaways.detailed: provide sections for Summary, Key Findings, Implications, and Recommendations.deep_dive: provide an executive summary, detailed analysis, data points, risks, opportunities, and actionable recommendations.
Edge cases
If topic is missing or blank, write a short markdown error note explaining that topic is required and call write_output with that note.
Output
Use markdown formatting. Do not include unsupported citations or fabricated source names. When the brief is ready, call finish_with_outputs with:
brief: the complete markdown brief
What ships with it
3 files 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 · 45 lines · 0 tokens per session scan A 15101763c1fd
research_brief is a skill published in the GitHub repository floomhq/floom (47 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 432 tokens. 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_brieffloomhq/floom | Skill | 47 | 1mo ago | MIT | A | 0 | Claude Code, Codex |
| arkcli-genvolcengine/ark-cli | Skill | 149 | 9d ago | Apache-2.0 | A | 88 | Claude Code, Codex |
| arkcli-modelsvolcengine/ark-cli | Skill | 149 | 9d ago | Apache-2.0 | A | 311 | Claude Code, Codex |
| arkcli-doctorvolcengine/ark-cli | Skill | 149 | 9d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| arkcli-plansvolcengine/ark-cli | Skill | 149 | 9d ago | Apache-2.0 | A | 375 | Claude Code, Codex |
| arkcli-docsvolcengine/ark-cli | Skill | 149 | 9d ago | Apache-2.0 | A | 109 | Claude Code, Codex |
| arkcli-sharedvolcengine/ark-cli | Skill | 149 | 9d ago | Apache-2.0 | A | 161 | Claude Code, Codex |