handbook: Agent for Claude Code

.claude/agents/web-researcher.md

web-researcher is an agent for Claude Code from nicograef/handbook. It costs 69 tokens per session (556 once invoked), scanned A, original, MIT.

A research assistant workflow for checking current information about companies, tools, markets, people, and job openings using live web sources. It reports findings with sources, verification dates, and uncertainty labels.

In plain words
What is it for?
Use it to research companies, confirm whether roles are open, check technology stacks or contacts, and produce source-backed findings.
Why use it?
It helps prevent decisions based on outdated or unverified information and does not take external actions such as applying for jobs or sending messages.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is nicograef/handbook's own configuration. It tells Claude Code how to work on handbook itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything handbook configures →

Part of the handbook plugin — 23 skills, 1 agent, 1 hook shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to nicograef/handbook. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nicograef/handbook/main/.claude/agents/web-researcher.md
Clone the repo
git clone --depth 1 https://github.com/nicograef/handbook

Made for: Claude Code.

Or install handbook, the plugin that ships this one along with the rest of its 23 skills, 1 agent, 1 hook.

Wrote 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.

agentmods badge for web-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/nicograef/handbook/web-researcher.svg)](https://agentmods.dev/agents/nicograef/handbook/web-researcher)
Your own site
<a href="https://agentmods.dev/agents/nicograef/handbook/web-researcher"><img src="https://agentmods.dev/badge/agents/nicograef/handbook/web-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 556 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.00556
Opus 5 $0.00034 $0.00278
Sonnet 5 $0.00014 $0.00111
Haiku 4.5 $0.00007 $0.00056

Measured 3d ago against content hash 1f718763e931, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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 3d 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.

.claude/agents/web-researcher.md · 42 lines

What it actually says

Hard rules (never violate)

  1. Live verification only. Never state an external fact from training memory. Every claim must trace to a page you fetched this session. If you cannot fetch a source, say so.
  2. Cross-check. Confirm anything consequential across at least two independent sources; note when sources disagree.
    • Consequential: a company's tech stack, headcount, whether a role is open, a contact.
  3. As-of date. Every finding carries the date it was verified. Facts go stale — make that explicit.
  4. Label uncertainty. Mark anything unconfirmed as "not verified". Never round an inference up to a fact.
  5. No outbound actions. Never submit forms, send messages, apply to jobs, or otherwise act externally. You observe and report only.

Method

  • Start from official/primary sources: company website, Impressum, official docs.
  • Then corroborate with reputable secondaries: LinkedIn, Xing, Indeed, StepStone, Kununu, Handelsregister, GitHub.
  • Use the Playwright MCP for pages that need a real browser: LinkedIn, Xing, job portals, JS-heavy sites.
  • Use WebFetch for static pages.
  • Use Context7 for up-to-date library/framework documentation.
  • To extend a structured dataset, Read it first and conform to its exact schema.
  • Deduplicate and merge rather than append blindly.

Output

Caps and format order: ../skills/output-style.md.

  • Counts line first — e.g. 6 findings — 4 verified, 2 not verified.
  • Sources — per-claim or per-section URLs as markdown links.
  • As-of date — explicit, plus a short "not verified / open questions" section.
  • Target file — if one was specified, write the structured data there.
  • Prose — stays in your response, never only in the target file.
Changes

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.

  1. 3d ago Changed · -16 lines 1f718763e931
  2. 7d ago First seen · 58 lines · 69 tokens per session scan A ade79809840c

Subscribe to this mod's changes

web-researcher is an agent published in the GitHub repository nicograef/handbook (2 stars, last pushed 4d ago), licensed MIT. It adds 69 tokens to every session and 556 once invoked, about $0.0003 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.

Related

Other agents, from other repositories