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 davidtoby/agent-skills --skill web-research-monitoring-workflowsgit clone --depth 1 https://github.com/davidtoby/agent-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/davidtoby/agent-skills/web-research-monitoring-workflows)<a href="https://agentmods.dev/skills/davidtoby/agent-skills/web-research-monitoring-workflows"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/web-research-monitoring-workflows/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/davidtoby/agent-skills/web-research-monitoring-workflows"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/web-research-monitoring-workflows.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 | $0.00078 | $0.00956 |
| Opus 5.5 | $0.00031 | $0.00382 |
| Sonnet 5.5 | $0.00016 | $0.00191 |
| Haiku 4.5 | $0.00008 | $0.00096 |
Grade A, and why
web-research-monitoring-workflows 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Research and Monitoring Workflows
Use this umbrella for information retrieval that is not tied to one site-specific API.
Core workflow
- Classify the retrieval need: one-shot search, fresh news, source monitoring, transcript lookup, broad summary, or recurring digest.
- Choose the source path:
- Search APIs/CLIs for broad discovery.
- RSS/Atom/Google News RSS for fresh public news and blocked/rate-limited search.
- Blog watcher feeds for recurring source monitoring.
- YouTube transcript tools for video-content questions.
- Summarizer CLI for known URLs/files.
- Gather more than one source for factual claims unless the user asks for a single-source summary.
- Preserve links, timestamps, publication dates, and provider used.
- For digests, de-duplicate, rank by relevance, and deliver a concise card/report in the requested language.
Labeled playbooks
Search provider selection
Use Brave/Tavily/multi-engine search depending on availability, locality, freshness, and whether AI-optimized snippets or raw web results are needed.
Google News RSS fallback
When normal search is blocked or stale, use Google News RSS, then open the canonical publisher pages for verification.
Blog/RSS monitoring
Store feed lists explicitly, track seen item IDs/URLs, and summarize only new items.
Recurring digest cron jobs
Create self-contained cron prompts with source list, timezone, delivery target, duplicate-job cleanup expectations, and output format.
For scheduled news-card jobs, treat the final response as the delivery payload: do not call messaging tools unless explicitly instructed by a live user. When the prompt asks for a Feishu/Lark-card feel in Markdown, preserve the requested column order and use compact card hierarchy: date title, one-line subtitle, 2-sentence summary, 3 bullets, visual dividers, then each item as title + core content + impact/practical note + inline canonical source link. Avoid AI framing phrases and do not bundle links at the end.
What ships with it
10 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.
- references/from-openclaw-imports-blogwatcher.md 1.7 KB
- references/from-openclaw-imports-brave-search.md 13204 KB
- references/from-openclaw-imports-multi-search-engine.md 30 KB
- references/from-openclaw-imports-summarize.md 1.9 KB
- references/from-openclaw-imports-tavily-search.md 5.3 KB
- references/from-openclaw-imports-youtube-watcher.md 4.3 KB
- references/from-productivity-rss-news-fetcher.md 6.6 KB
- references/from-research-follow-builders-cron-digest.md 4.8 KB
- references/from-research-google-news-rss-digesting.md 11 KB
- references/from-research-wechat-business-news-cron.md 12 KB
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 · 71 lines · 78 tokens per session scan A 0eb60cfb37c1
web-research-monitoring-workflows is a skill published in the GitHub repository davidtoby/agent-skills (11 stars, last pushed 2mo ago), licensed MIT. It adds 78 tokens to every session and 956 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
LLM
Implement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to build conversational AI applications, chatbots, AI assistants, or any text generation features. Supports multi-turn conversations, system prompts, and context management.
optimize-prompt
Optimize Claude Code and LLM prompts for token efficiency, prefix caching compliance, positional recall, and execution correctness. Use when writing/reviewing prompts, debugging agent errors/failures, managing context windows, selecting effort levels, choosing MCP vs CLI tools, designing subagents, or editing…
ai-teacher
A guide to teaching about artificial intelligence, including how large language models work, prompt writing, AI agents, tools, and AI ethics.
write-a-prompt
Creates a copy-ready prompt from a rough request, notes, source material, or the current conversation using OpenAI's prompting guidance. Use when the user invokes $write-a-prompt or /write-a-prompt, types a common misspelling such as /write-a-promopt or /wite-a-prompt, asks to "write a prompt for me," asks to turn the…
promptify
Transform user requests into detailed, precise prompts for AI models. Use when users say "promptify", "promptify this", or explicitly request prompt engineering or improvement of their request for better AI responses.
ehr-analysis
End-to-end EHR predictive modeling pipeline with PyHealth, covering dataset loading, task definition, model training, evaluation, calibration, and clinical interpretation.