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 alexei-led/cc-thingz --skill researching-webgit clone --depth 1 https://github.com/alexei-led/cc-thingzWrote 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/alexei-led/cc-thingz/researching-web)<a href="https://agentmods.dev/skills/alexei-led/cc-thingz/researching-web"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/researching-web/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/alexei-led/cc-thingz/researching-web"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/researching-web.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00075 | $0.00732 |
| Opus 5 | $0.00037 | $0.00366 |
| Sonnet 5 | $0.00015 | $0.00146 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
researching-web 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Research
Use web tools for grounded external research. Prefer primary sources, official docs, and current evidence. Do not answer from memory when the user asked for research.
Scope
Use this for:
- comparisons and trade-offs
- recent facts, current-state questions, and release behavior
- standards and external best practices
- ecosystem, licensing, or market facts
- vendor docs as evidence for non-syntax claims
Do not use this for:
- exact API syntax, config keys, or code examples →
looking-up-docs - repo-specific questions that local files can answer
- private code, secrets, credentials, or proprietary data
Tool selection
Choose tools by question type:
- Simple factual question: use the platform's focused answer or search tool.
- Source selection: search first, then fetch or read the best official or primary sources.
- Broad investigation: use deep or asynchronous research when available.
- Follow-up detail on a cited source: fetch the relevant source directly.
Do not hardcode one provider as the answer for every question. Use the tool that best matches the question and the available runtime.
Workflow
- Restate the research question and the decision it should inform.
- Decide whether the question is simple, source-selection, or broad investigation.
- Gather sources with the matching tool.
- Prefer primary or official sources when they can answer the question.
- Compare sourced facts against local project constraints before recommending changes.
- Separate sourced facts from recommendation or judgment.
- Report unknowns, stale-source risk, and gaps directly.
If the user asks for the workflow itself, describe the source-gathering plan and output structure; do not present an uncited recommendation as fact.
Conditional References
- sources.md — read when choosing between web tools or evaluating source quality: tier ranking, stale-source detection, platform-specific tool guidance (Pi
web_search/web_answer/web_research), source caching.
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.
- 9d ago First seen · 102 lines · 75 tokens per session scan A 09725105ba76
researching-web is a skill published in the GitHub repository alexei-led/cc-thingz (35 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 732 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 2026-08-30.
Other skills, from other repositories
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
sdd-verify
Skill "sdd-verify" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, activation contract, hard rules and decision gates.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
cognitive-doc-design
Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.