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 alfredxw/denova --skill web-researchgit clone --depth 1 https://github.com/alfredxw/denovaWrote 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/alfredxw/denova/web-research)<a href="https://agentmods.dev/skills/alfredxw/denova/web-research"><img src="https://agentmods.dev/badge/skills/alfredxw/denova/web-research.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.01018 |
| Opus 5 | $0.00018 | $0.00509 |
| Sonnet 5 | $0.00007 | $0.00204 |
| Haiku 4.5 | $0.00004 | $0.00102 |
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 9d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Research
Turn an open-ended question into a bounded, evidence-backed answer. Use search results to discover sources, fetch the promising pages, verify the important claims, and cite what actually supports the answer.
Do not use this workflow for a stable fact already known with high confidence or a simple transformation of text the user already supplied. If either required web tool is unavailable, state that limitation instead of pretending to have researched the web.
Workflow
-
Define the research target.
- Identify the decision or question, relevant region, time window, and what would count as sufficient evidence.
- Resolve ambiguity with a reasonable stated assumption when possible. Ask only when different interpretations would materially change the result.
- For vague terms such as “best,” “popular,” or “safe,” translate the term into observable criteria before searching.
-
Plan distinct search angles.
- Start with 2–4 meaningfully different queries, not repeated paraphrases. Cover the direct question, likely primary sources, an independent verification angle, and recency or criticism when relevant.
- Put distinctive subjects, organizations, products, or domains early in each query. Avoid generic prefixes that can dominate matching, especially for Chinese current-events or trend searches.
- Use
time_rangewhen freshness matters, but treat it as a best-effort filter and verify dates on fetched pages.
-
Discover candidate sources with
web_search.- Read
warningson every response. Partial provider failure does not invalidate good results, but it reduces coverage and may justify one focused follow-up query or a configured SearXNG source. - Treat search snippets as discovery hints, never as evidence for a final claim.
- Prefer primary sources for first-party facts, official data, specifications, laws, and original research. Add independent sources for interpretation, criticism, comparisons, or disputed claims.
- Avoid counting mirrors, syndications, or several pages repeating one press release as independent evidence.
- Read
What ships with it
1 file 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.
- 9d ago First seen · 53 lines · 37 tokens per session scan A 75ba1dbe8639
web-research is a skill published in the GitHub repository alfredxw/denova (696 stars, last pushed yesterday), licensed Apache-2.0. It adds 37 tokens to every session and 1,018 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
llmlint
A Chinese-prose rule library with two entry points. Before writing, emit the rules as writing constraints to load into a system prompt or style guide. After writing, lint the draft with static rule hits, neural AIGC heatmaps, contextual review, approved repair, and local learning notes. Use when drafting or rewriting…
profile-system-guide
Guide users and agents through Neuro Book harness, TSX profiles, ProfileTurnPlan, skills, user-assets overlays, settings forms, profile home resources, profile compile checks, templates, system restore, and safe profile editing.
novel-technique-character-card-workshop
A workshop for turning rough character ideas into detailed, usable character profiles. It supports structured question cycles, personality layers, visual themes, and checks against reducing a character to a few labels.
RP模式
A set of instructions for running a role-playing session under the NeuroBook RP protocol. RP means role-play, where characters and events are simulated according to defined rules.
novel-writer-execution
An internal execution guide for a writer profile after it receives a brief. It describes the detailed workflow, decision points, and common mistakes.
skill-creator
Create or update a Neuro Book skill under .nbook/agent/skills. Use this when you need to design a new skill, refactor an existing skill, tighten trigger descriptions, reorganize bundled resources, or add optional helper scripts and references for the project skill system.