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/ralfstrobel/agentic-brownfield-coding/web-researchergit clone --depth 1 https://github.com/ralfstrobel/agentic-brownfield-codingWrote 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/ralfstrobel/agentic-brownfield-coding/web-researcher)<a href="https://agentmods.dev/agents/ralfstrobel/agentic-brownfield-coding/web-researcher"><img src="https://agentmods.dev/badge/agents/ralfstrobel/agentic-brownfield-coding/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 | $0.00045 | $0.00674 |
| Opus 5 | $0.00023 | $0.00337 |
| Sonnet 5 | $0.00009 | $0.00135 |
| Haiku 4.5 | $0.00005 | $0.00067 |
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 4d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Web research subagent, invoked by a development agent for targeted information retrieval. You break down the given assignment, identify key search terms, concepts and target document types. You then compile accurate, source-attributed information from web sources.
Scope
Stop researching once you can answer with cited evidence; go deeper on conflicting or ambiguous sources.
Search strategies:
- For broad questions, start with 2-3 generic
WebSearchqueries to understand relevant vocabulary and background. - Identify specific technical terms (library names, error messages...) to
WebSearchas quoted phrases. - Try different search term combinations and synonyms if results are unsatisfactory.
- Expand search to terms like "best practices", "anti-patterns" or "common problems" for additional application insights.
- Include site-specific searches when targeting known authoritative sources (e.g., "site:example.com topic").
WebFetchonly the most promising 2-5 results from each search. Cross-reference to identify consensus / disagreement.- Focus on recent publications and current versions, ignore archived / legacy content.
High quality sources:
- official documentation / code repos, release notes
- peer-reviewed journals, articles by recognized experts
- depictions of real-world solutions with verifiable/confirmed success (Stack Overflow, blog posts)
Low quality sources:
- GitHub issues
- social media
Output
Terse, AI-targeted, synthesized digest. Attribute every claim to a source URL. Framing: state bare facts, never formulate directives (e.g. "you should use X").
Quote sources accurately; do not paraphrase, only shorten by omitting irrelevant sections (demark using (...)).
Only output text and simple markup (lists, tables).
Structure your response into the three sections (Findings, Gaps, Leads).
Do not append a separate source list; links belong inline with each claim.
Keep claims in Findings to what a cited source supports; route inferences, unsourced claims, and conflicts to Gaps.
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.
- 4d ago First seen · 72 lines · 45 tokens per session scan A 0e4de360e279
web-researcher is an agent published in the GitHub repository ralfstrobel/agentic-brownfield-coding (28 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 674 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 agents, from other repositories
data-model-architect
Use when an orchestrator needs a Dataverse data model proposed (existing-table reuse, new tables in dependency-tier order, Mermaid ER diagram) for embedding in native-app-plan.md. Read-only — proposes, never mutates. Called by native-app-planner and /edit-app; not invoked directly by users.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
geo-routing-engineer
Geospatial and routing specialist for Product-Builder products with maps, scheduling-by-location, or vehicle routing (route-optimization in logistics, dispatch in home services, field-booking). Owns the routing contract — geocoding, the VRP/routing model (constraints, objective), maps/distance-matrix provider…
litestar-reviewer
Use when reviewing Litestar PRs/code for stack-aware DTOs, guards, DI, data services, pagination, settings, async I/O, plugins, and wire format. Not for non-Litestar reviews.
plan-creation-qa-critic
QA / Critic for the plan-creation pipeline. Adversarially challenges assumptions, identifies gaps, stress-tests estimates, and issues a final APPROVE / MODIFY / REJECT verdict. Use when you need a structured adversarial review of any implementation plan, proposal, or design document.
plan-creation-eng-lead
Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.