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 desy-design/AG3NT --skill web-researchgit clone --depth 1 https://github.com/desy-design/AG3NTWrote 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/desy-design/ag3nt/web-research)<a href="https://agentmods.dev/skills/desy-design/ag3nt/web-research"><img src="https://agentmods.dev/badge/skills/desy-design/ag3nt/web-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/desy-design/ag3nt/web-research"><img src="https://agentmods.dev/badge/skills/desy-design/ag3nt/web-research.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 | $0.00017 | $0.00831 |
| Opus 5.5 | $0.00007 | $0.00332 |
| Sonnet 5.5 | $0.00003 | $0.00166 |
| Haiku 4.5 | $0.00002 | $0.00083 |
Grade A, and why
web-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 1mo 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.
This is a copy
100% identical to web-research — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Research Skill
Use this skill when the user needs:
- Current information on any topic
- Comparison between products, services, or concepts
- Documentation or official sources
- News or recent developments
- Cited summaries with sources
Research Workflow
Step 1: Plan Your Research
Before searching, define:
- Main question: What specifically does the user want to know?
- Subtopics: Break complex topics into 2-3 focused areas
- Source types: What kinds of sources are most relevant?
- Documentation (official docs, specs)
- News (recent articles, announcements)
- Academic (papers, research)
- Community (forums, discussions, reviews)
Step 2: Search and Gather
For each subtopic:
- Run 2-3 targeted searches using the web_search tool
- Evaluate sources for credibility:
- Official domains (.gov, .edu, company sites)
- Publication date (prefer recent for evolving topics)
- Author expertise
- Extract key information and note the source URL
Step 3: Organize Findings
Create a structured output:
## Research: [Topic Name]
### Key Findings
- Finding 1 [Source](url)
- Finding 2 [Source](url)
### Detailed Summary
[Synthesis of information with inline citations]
### Sources
1. [Title](url) - Brief description of what this source provided
2. [Title](url) - Brief description of what this source provided
Step 4: Synthesize and Respond
When presenting to the user:
- Lead with the answer - Don't bury the key information
- Provide context - Why is this relevant?
- Cite sources - Use inline links or footnotes
- Note limitations - If information is incomplete or conflicting, say so
Citation Format
Use this format for citations:
- Inline:
According to [Source Name](url), ... - Footnote:
Key fact here[^1]with[^1]: Source Name - url - List: See references/citation-format.md for detailed examples
Quality Checklist
Before finishing research:
- Answered the user's core question
- Used at least 2-3 distinct sources
- Cited all factual claims
- Noted if information is dated or incomplete
- Provided actionable next steps if relevant
What ships with it
2 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.
- 1mo ago First seen · 118 lines · 17 tokens per session scan A 296e96d2aa85
web-research is a skill published in the GitHub repository desy-design/AG3NT (2 stars, last pushed 12d ago), licensed MIT. It adds 17 tokens to every session and 831 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to web-research, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
web-research
Structured approach to conducting thorough web research with citations and organized output.
status-card-query
Create and maintain agent-authored Paperclip status cards, or compile a prose interest prompt into bounded CompanySearchQuery objects and write the first summary from the assigned Summarizer run.
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
paperclip
Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.
paperclip-board
Manage a Paperclip company as a board member via chat. Use when the user wants onboarding, company or agent management, approvals, task monitoring, cost oversight, or work product review in the Paperclip control plane.
paperclip-distill
Use when an operation issue is a Paperclip cursor-window, distill, or backfill. Turn source-bundled Paperclip activity into wiki-insightful project standups, durable project pages, decisions, and history without asset dereferencing.