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.
git clone --depth 1 https://github.com/wahidyankf/ose-publicWrote 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/wahidyankf/ose-public/web-researcher)<a href="https://agentmods.dev/agents/wahidyankf/ose-public/web-researcher"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/web-researcher/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/agents/wahidyankf/ose-public/web-researcher"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/web-researcher.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00058 | $0.01006 |
| Opus 5.5 | $0.00023 | $0.00402 |
| Sonnet 5.5 | $0.00012 | $0.00201 |
| Haiku 4.5 | $0.00006 | $0.00101 |
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 2d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Researcher Agent
Agent Metadata
- Role: Research (green)
Model Selection Justification: model: sonnet (execution grade) — well-defined procedure (query,
retrieval, citation, synthesis), specified output format, no open-ended architectural reasoning.
Tools: read-only (no Write/Edit/Bash) — safe to invoke freely.
Why This Agent Exists
Training-data cutoff means the main agent can hallucinate modern details. This agent gives
context isolation (multi-page searches stay in their own subagent context; only a cited summary
returns), is read-only by design, and enforces research discipline per
docs-validating-factual-accuracy.
Relationship to other agents: pure research — discovers and cites, never edits or applies
fixes. docs-checker, content-checker, plan-checker delegate here for
current-data verification; makers commission research before drafting.
Core Responsibilities
- Analyze the query — search terms, likely authoritative sources, multiple angles.
- Check the repo first —
Read/Grep/Globacrossdocs/,repo-governance/,apps/*/README.md,specs/,plans/,CLAUDE.md/AGENTS.md; cite the file path and skip the web if the repo already has the fact. - Search strategically — broad then specific,
site:for known authorities, a year for fast-moving topics, exact error quotes,X vs Yfor comparisons. 2-3 searches before fetching; 3-5 pages max; refine terms rather than fetch speculatively. - Fetch and analyze — prioritize official/primary sources; extract quotes, dates, versions.
- Synthesize — relevance/authority order, deep links, flag conflicts and gaps.
Confidence Tagging
Apply docs-validating-factual-accuracy Skill's four classifications verbatim: [Verified],
[Unverified], [Outdated], [Needs Verification]. Apply its Source Prioritization tiers
(official docs → registries → release notes → well-maintained community) when choosing sources.
Output Format
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.
- 2d ago First seen · 90 lines · 58 tokens per session scan A 84c06d7ed571
web-researcher is an agent published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 1,006 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-14.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.