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 agentmods add skills/oleg494/coding-kit/web-researchnpx skills add oleg494/coding-kit --skill web-researchgit clone --depth 1 https://github.com/oleg494/coding-kitWhat 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 | $0.00078 | $0.00698 |
| Opus 5 | $0.00039 | $0.00349 |
| Sonnet 5 | $0.00016 | $0.00140 |
| Haiku 4.5 | $0.00008 | $0.00070 |
Grade A, and why
web-research scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **Web search.** Use the available tools (web_search, curl, browser). How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Research — facts from the outside world
Workflow
- Formulate your search query. What exactly do you need to find out? 2-3 wordings.
- Web search. Use the available tools (web_search, curl, browser).
- Primary sources, not retellings. Official docs > articles > forums. Don't trust retellings without a link to the original.
- Cross-check. Minimum 2 independent sources for each key fact. 1 source = not an answer.
- Dating. When is the data current? "As of August 2026..."
- Answer with sources. Every fact with a link. Mark unverified claims "verify".
Source hierarchy & fallback (403/429/captcha)
- Official docs / GitHub repo / source code — the primary source.
- Issue trackers, ADRs, engineering blogs — industry practice.
- Direct HTTP fetch of the page (
readon the URL) — when search engines block you.
On 403/429/captcha: switch to the next level immediately; never stop the task and never fill the gap by inventing a result. If every level fails: "not verified — sources unreachable", and name exactly what was tried.
Research depth
- Quick fact (date, number, definition) — 2-3 sources, one pass.
- Medium research (comparison, "how it works") — 5-7 sources, primary sources + expert articles.
- Deep research (strategy, technology choice, "what do they say about") — 10+ sources, breadth → depth: canonical repos, PRs, issues, ADRs, official guides.
What to look for
| Type of information | Where to look |
|---|---|
| API / library | Official documentation, GitHub README, source code |
| Industry practice | GitHub issues, ADRs, engineering blogs, Thoughtworks Tech Radar |
| Bug / error | GitHub issues, Stack Overflow, official bug tracker |
| Tool comparison | Benchmarks, practitioner articles, Hacker News discussions |
| Regulations / laws | Official sources (.gov, legal databases) |
Answer
- Result first line. What was found, briefly.
- Details with sources. Every fact with a link.
- Caveats. What wasn't verified, what's in question.
- Offer to save. "Save this in the Wiki?"
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.
- yesterday First seen · 56 lines · 78 tokens per session scan A f47d6e73edf9
web-research is a skill published in the GitHub repository oleg494/coding-kit (1 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 698 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
run
Execute a named agent role with optimized instructions. Explicit invocation only ($run). Never trigger implicitly.
tip
Deliver a transformative life perspective shift and a productivity tip. Use when the user invokes /tip or wants non-technical inspiration or a fresh mental model.
agentic-security-review
Run a security and dependency audit for agent systems, tool-using AI apps, MCP/A2A integrations, or security-sensitive AI-generated code. Check slopsquatting risk, tool shadowing, rug pulls, memory/context poisoning, secrets, unsafe permissions, and common CWE patterns. Use when asked for security review, dependency…
agentic-spec
Create a structured specification before agentic coding work. Assemble the six context types, scale rigor for prototype/internal/production tasks, produce SPEC.md, and configure focused AGENTS.md boundaries. Use when asked to write a spec, plan a feature, design an agent/system, define architecture, or create…
agentic-evals
Design evaluation contracts and test plans for agentic systems. Create deterministic tests, trajectory evals, quality dimensions, gold-set criteria, and CI gates before or after implementation. Use when asked for tests first, an eval plan, success criteria, non-deterministic testing, LLM-as-judge setup, or…
agentic-production-readiness
Prepare an AI agent system for production operation. Cover SHIELD controls, sandbox/canary/production rollout, OpenTelemetry observability with GenAI semantic conventions, Agent Card drafting, governance, and post-deploy monitoring. Use for production readiness checks, go-live checklists, agent monitoring, agent…