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 naveedharri/benai-skills --skill researchgit clone --depth 1 https://github.com/naveedharri/benai-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/naveedharri/benai-skills/research)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/research"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/research/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/naveedharri/benai-skills/research"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Memory Poisoning · line 35 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
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 | $0.00089 | $0.00582 |
| Opus 5 | $0.00044 | $0.00291 |
| Sonnet 5 | $0.00018 | $0.00116 |
| Haiku 4.5 | $0.00009 | $0.00058 |
Grade A, and why
research 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 7d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
Turns a research request into a comprehensive, sourced report using the OpenAI Deep Research API. The orchestration script assesses the prompt, enhances it through clarifying questions when needed, saves the exact prompt for reproducibility, runs the research, and saves a markdown report with numbered sources.
Steps
-
Accept the user's research request (brief or detailed).
-
Decide whether to enhance. If the prompt is brief or generic, ask the 2-3 clarifying questions in
references/prompt-enhancement.md(present numbered options plus a free-text option) and build the enhanced prompt. Skip when the prompt is already specific. -
Confirm the final prompt with the user before executing. A run costs API spend and takes 10-20 minutes, so get a yes on the enhanced prompt first.
-
Run the orchestration script:
python3 scripts/run_deep_research.py "<prompt>"It re-runs the enhancement check, saves
research_prompt_*.txt, and executes synchronously. Options and output files are inreferences/cli.md. Wait silently for completion; do not poll for status. -
Present results: the markdown report (
research_report_*.md), the numbered source URLs, and the saved file paths. Offer follow-up research directions.
Routing
references/prompt-enhancement.md: when to enhance, the question templates (technical vs general), how to build the enhanced prompt, worked examples.references/cli.md: script options, output files, execution behavior.references/troubleshooting.md: requirements and error fixes (missing API key, script not found, timeout).
Self-improvement
This skill is never finished. Improve it as you use it.
- When the user corrects how a step was done, update the relevant reference file (or this SKILL.md) so the correction sticks. Do not just fix it for this run.
- When a correction is a hard rule ("always X", "never Y"), add it as a permanent rule here.
- When the user says a research report was genuinely good, save it to
references/examples/so it becomes a model for future runs. - Keep the skill small: when you add something, run the deletion test and cut anything that no longer changes behavior.
What ships with it
6 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.
- 7d ago First seen · 38 lines · 89 tokens per session scan A fac46c7ff761
research is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 582 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
project
A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.
doc-html-slide
A renderer that turns presentation content into a single HTML slide deck that opens directly in a browser. It creates a 16:9 slide sequence with navigation, fullscreen viewing, printing to PDF, and speaker-note controls.
cs-channel-message
A channel-message writing tool for search ads, advertising, customer relationship messages, and app notifications. It uses the NCM sequence—Need, Channel, Moment, Message, and CTA—to adapt wording to where and when customers see it.
design-tokens-transformer
A converter for design tokens, which are named values for colors, fonts, spacing, borders, shadows, and motion. It translates one shared token source into CSS variables and Tailwind or shadcn-style theme files, and can convert them back for checking.
media-higgsfield-explainer
A Higgsfield workflow for making non-photorealistic narrated explainer videos. It pairs each narration line with a 10-second animated clip and joins the clips into one finished video.