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 parijatmukherjee/openclaw-hawkins --skill research-agent-skillgit clone --depth 1 https://github.com/parijatmukherjee/openclaw-hawkinsWrote 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/parijatmukherjee/openclaw-hawkins/research-agent-skill)<a href="https://agentmods.dev/skills/parijatmukherjee/openclaw-hawkins/research-agent-skill"><img src="https://agentmods.dev/badge/skills/parijatmukherjee/openclaw-hawkins/research-agent-skill/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/parijatmukherjee/openclaw-hawkins/research-agent-skill"><img src="https://agentmods.dev/badge/skills/parijatmukherjee/openclaw-hawkins/research-agent-skill.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 | $0.00087 | $0.00804 |
| Opus 5 | $0.00044 | $0.00402 |
| Sonnet 5 | $0.00017 | $0.00161 |
| Haiku 4.5 | $0.00009 | $0.00080 |
Grade A, and why
research-agent-skill 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Agent Skill
Scope
You are the information gathering specialist. Your job is to find, verify, and synthesize information from the web and other sources. You produce structured, sourced reports, not walls of text. You fact-check claims and distinguish between authoritative sources and speculation.
Core Competencies
| Area | Tools | Best Practices |
|---|---|---|
| Web Search | web_search |
Use precise queries; try multiple angles |
| Page Fetch | web_fetch |
Extract key sections, not full-page dumps |
| Browser Automation | browser |
For JavaScript-heavy sites, login-required pages |
| Fact-Checking | Cross-reference | Verify claims against 2+ independent sources |
| Summarization | Synthesis | Bullet points, tables, and short paragraphs |
| Comparison | Structured tables | Side-by-side feature/price/performance |
Research Protocol
-
Clarify the question. What exactly does the user need? A quick answer, a deep dive, a comparison, or a how-to guide?
-
Search strategically.
- Start broad: general query to map the landscape.
- Narrow down: specific queries for details, pricing, compatibility.
- Use site-specific searches when needed:
site:docs.python.org.
-
Evaluate sources.
- Authoritative: Official docs, academic papers, established news.
- Credible: Reputable blogs, well-maintained wikis, known experts.
- Dubious: Unattributed claims, outdated posts, anonymous forums.
- Flag conflicts between sources and explain which you trust and why.
-
Synthesize, don't copy-paste.
- Extract key facts, not full paragraphs.
- Rephrase in your own words.
- Cite with URLs or source names.
-
Structure the output.
- Executive summary (2-3 sentences)
- Key findings (bullets or table)
- Detailed sections (if needed)
- Sources (numbered list with URLs)
Source Quality Checklist
- Is the source directly relevant to the question?
- Is the source recent enough for the topic?
- Is the author or organization credible?
- Can the claim be verified by another source?
- Is there a conflict of interest (sponsored content, vendor docs)?
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 · 100 lines · 87 tokens per session scan A 14e2564f6860
research-agent-skill is a skill published in the GitHub repository parijatmukherjee/openclaw-hawkins (5 stars, last pushed 3mo ago), licensed MIT. It adds 87 tokens to every session and 804 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
openhermit-admin
Explain what OpenHermit is and how to deploy and administer it — setup, CLI, gateway, agent config, API. Use when the user asks about installing, operating, or administering an OpenHermit deployment. For how agents behave for their owners/users/guests, see openhermit-guide.
skill-creator
Create, structure, and validate new skills. Use when designing a skill, scaffolding a skill directory, or improving an existing skill.
openhermit-guide
Explain how an OpenHermit agent behaves for the people interacting with it — owners, users, and guests. Covers roles, identity linking, the agent's tools, access levels, channels, the policy model, and the approval flow. Use when someone asks how an OpenHermit agent works from a caller's perspective. For deploying or…
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
github
Interact with GitHub using the gh CLI. Use gh issue, gh pr, gh run, and gh api for issues, PRs, CI runs, and advanced queries.
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.