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 TheCraigHewitt/cowork-starter-pack --skill research-briefgit clone --depth 1 https://github.com/TheCraigHewitt/cowork-starter-packWrote 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/thecraighewitt/cowork-starter-pack/research-brief)<a href="https://agentmods.dev/skills/thecraighewitt/cowork-starter-pack/research-brief"><img src="https://agentmods.dev/badge/skills/thecraighewitt/cowork-starter-pack/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/thecraighewitt/cowork-starter-pack/research-brief"><img src="https://agentmods.dev/badge/skills/thecraighewitt/cowork-starter-pack/research-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 | $0.00079 | $0.01210 |
| Opus 5 | $0.00039 | $0.00605 |
| Sonnet 5 | $0.00016 | $0.00242 |
| Haiku 4.5 | $0.00008 | $0.00121 |
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 11d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Brief
Turn "I need to know about X before my 2pm call" into a one-page brief the user can skim in three minutes and feel prepared.
Before starting
- Ask the user what they want a brief on if it's not clear. A company? A person? A topic? A competitor?
- Ask what they need the brief for. A sales call? A strategic decision? A blog post? Same subject, different briefs.
- Read
context/preferences.md— source citation style, confidence level tagging if relevant - Check the project folder — have you researched this subject before? Build on it, don't redo it.
What to produce
A markdown file saved to /output/research-brief-{subject}-{YYYY-MM-DD}.md with four sections:
- The 30-second version — three to five sentences. If the user only reads this section, what do they need to know?
- What they do / what it is — core facts. Company: product, size, customers, how they make money. Person: role, background, what they're known for. Topic: the basics.
- What matters right now — recent news, strategic shifts, public statements, anything timely. What's changed in the last 90 days.
- Sources & confidence — what you drew from, and where you're guessing vs. citing. Label each claim with a confidence marker if the user asked for it in
preferences.md.
Inputs
- Web search (required)
- The user's prior research on this subject in the project folder (if exists)
- Recent emails mentioning the subject (optional — useful for competitive briefs)
- Any docs the user uploaded with the request
How it works
- Understand the subject and the purpose (ask if unclear)
- Search the web — company site, news, LinkedIn if it's a person, press releases, recent podcast/video appearances for public figures
- Cross-reference with any existing project context
- Draft the four sections. Short. Dense with information. No padding.
- Flag anything uncertain or contested — never smooth over ambiguity
- Save the file, tell the user one-line what stood out ("Strong product, weak financials — the gap is interesting if you're pitching to them")
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.
- 11d ago First seen · 84 lines · 79 tokens per session scan A 0c14b5faf148
research-brief is a skill published in the GitHub repository TheCraigHewitt/cowork-starter-pack (5 stars, last pushed 4mo ago), licensed MIT. It adds 79 tokens to every session and 1,210 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 2026-08-31.
Other skills, from other repositories
findcoworkskills
Find skills you can install and use in Claude Cowork for a given topic. Use this skill whenever the user wants to discover existing skills before building their own — triggers include "find cowork skills for X", "what skills exist for X", "is there already a skill for X", "search for skills about X", "find me a skill…
watch-video
SLASH-COMMAND-ONLY. Invoke ONLY when the user explicitly types the literal /watch-video slash command. Never auto-trigger on phrases like "watch this video," "summarize this video," "take notes on this video," or on a bare YouTube URL. For ad-hoc YouTube questions, fetch the transcript directly (YouTube page or…
analytics-strategy
Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement.…
content-strategy
Develop a content strategy covering editorial positioning, content pillars, formats, calendar, governance, and topical authority planning. Use this skill whenever the user wants to plan a content program, define content pillars, build an editorial calendar, structure topic clusters, set up content governance, or align…
incident-response
Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured roles and decision-making. Use this skill whenever the user has an active incident, a production issue, a service outage, a security incident, or needs to plan incident response procedures. Triggers…
stakeholder-communication
Communicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates, preparing executive reviews, sharing technical decisions with non-technical audiences, managing up, communicating bad news, or designing the communication cadence for a project. Triggers on…