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 topic-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/topic-research)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/topic-research"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/topic-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/topic-research"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/topic-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 112 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 | $0.00223 | $0.02378 |
| Opus 5 | $0.00112 | $0.01189 |
| Sonnet 5 | $0.00045 | $0.00476 |
| Haiku 4.5 | $0.00022 | $0.00238 |
Grade A, and why
topic-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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Topic Research
Turns a topic into a rigorous, sourced, fact-checked report. Two artifacts come out every time: a markdown brief (agent-readable, the handoff to a content-writer skill) and a branded HTML report (human-facing, deployable). The workflow is: interview the user so the research is targeted, fan out parallel research sub-agents across source types, verify every hard claim, synthesize to markdown, render to HTML, deploy.
[!important] The two rules that make this good
- Targeted, not generic. The Phase 0 Q&A shapes every sub-agent. Research aimed at a purpose beats a topic dump every time.
- Verify before you publish. No hard number reaches the report without a fact-check verdict and a caveat. Fact and opinion stay visibly separate.
Phase 0: Targeted Q&A + capability probe
Do both before any research runs. Ask conversationally, one thing at a time, adapting to answers.
A. Targeted Q&A (this shapes the whole run)
- Topic, and what they already believe or suspect about it.
- Purpose: is this to write a specific piece of content (which format? which audience?), to make a decision, to brief a team, to prep for a talk? A content purpose changes what the report emphasizes and how the markdown is structured downstream.
- Angle / biases / skepticism to reflect: a point of view they want the research to support or pressure-test, claims they are suspicious of, hot takes to stress-test. These become explicit search directives for the sub-agents. If they have none, the research stays neutral and simply reports the tension it finds.
- Depth: Quick / Standard / Deep (see below).
- Output: report + markdown always; deploy target is a Claude live artifact (instant, no infra) or Vercel (stable custom URL). Ask which.
- Brand: default to the neo-brutalist "Signal Report" look in
assets/report-template.html. If they have a brand (site, design system, colors/fonts/logo), extract and restyle; the CSS is token-driven at the top of the template.
What ships with it
4 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 · 115 lines · 223 tokens per session scan A 3259a818f8c7
topic-research is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed today), licensed MIT. It adds 223 tokens to every session and 2,378 once invoked, about $0.0011 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.