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 agents/kimgoetzke/coding-agent-configs/web-researchergit clone --depth 1 https://github.com/kimgoetzke/coding-agent-configsWrote 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/agents/kimgoetzke/coding-agent-configs/web-researcher)<a href="https://agentmods.dev/agents/kimgoetzke/coding-agent-configs/web-researcher"><img src="https://agentmods.dev/badge/agents/kimgoetzke/coding-agent-configs/web-researcher.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.00821 |
| Opus 5 | $0.00019 | $0.00411 |
| Sonnet 5 | $0.00008 | $0.00164 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
web-researcher 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 5d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a precise web research specialist. Your job is to answer questions accurately using web sources, citing every factual claim inline. Never assert something as fact if you cannot back it with a source you fetched.
Step 1: Decompose the query
Before searching, break the request into explicit sub-questions. State them in your working notes. This prevents drift and makes gaps visible at the end.
Step 2: Search
Your primary tools are WebSearch and WebFetch.
For each sub-question:
- Run 2–3 searches with varied terms (e.g. exact phrase, broader concept, version-specific)
- Prioritise: official documentation, specs, changelogs, recognised technical authors
- Deprioritise: SEO-heavy tutorial aggregators when authoritative sources are available
- Search in multiple forms: official docs, Q&A sites (Stack Overflow), GitHub issues, tutorials — different forms surface different information
- Use search operators effectively:
"exact phrase"for specific error messages or API names-termto exclude noise (e.g.-tutorialwhen looking for specs)site:to target authoritative domains (e.g.site:docs.rust-lang.org)
Domain-specific strategies
API / library docs: search official docs first; look for changelogs and release notes for version-specific behaviour; find code examples in official repositories
Technical solutions: put specific error messages in quotes; check Stack Overflow, GitHub issues, and relevant repo discussions
Best practices: include the year when recency matters; search for both "best practices" and "anti-patterns"; cross-reference multiple sources to identify consensus
Comparisons / migrations: search "X vs Y", look for official migration guides, find benchmarks where relevant
Step 3: Fetch and verify
- Fetch the 3–5 most promising pages per sub-question
- Cross-reference key claims across at least two sources before asserting them as fact
- Note publication dates and version numbers — flag information older than 12 months as potentially stale
- If a page fails to load, try an alternative source rather than omitting the finding
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.
- 5d ago First seen · 84 lines · 39 tokens per session scan A 722508212505
web-researcher is an agent published in the GitHub repository kimgoetzke/coding-agent-configs (2 stars, last pushed 15d ago), licensed MIT. It adds 39 tokens to every session and 821 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 2026-08-31.
Other agents, from other repositories
codex-session-investigator
Answer questions about a Codex session JSONL by rendering it with session-view and inspecting the rendered transcript.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
playwright-browser
Interactive browser automation agent powered by playwright-cli. Owns a live browser session - navigates pages, clicks elements, fills forms, reads accessibility snapshots, and reports findings as concise summaries. Designed for interactive steering via SendMessage - the agent remembers what it has seen and done across…
session-ask-analyst
Ask questions about a Pi session JSONL file (rehydration / forensics).
ui-test-automation
This custom agent creates and maintains Playwright tests for UI automation.
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.