source-inspector

source-inspector is an agent for Claude Code from cogni-work/insight-wave. It costs 151 tokens per session (1,233 once invoked), scanned A, original, Apache-2.0.

A browser-based source-checking agent that opens a supplied URL, finds a relevant passage, and shows the surrounding evidence to the user. It requires the Claude-in-Chrome browser extension to be installed and connected.

In plain words
What is it for?
Inspecting source pages, locating quoted passages, and presenting evidence when a reported deviation needs the user's review.
Why use it?
It helps verify a claim against the live source instead of relying only on a copied excerpt or an agent's interpretation.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the cogni-workspace plugin — 5 skills, 2 commands, 19 agents shipped together

Good fit Inspecting source pages, locating quoted passages, and presenting evidence when a reported deviation needs the user's review.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cogni-work/insight-wave/source-inspector
Install

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.

Clone the repo
git clone --depth 1 https://github.com/cogni-work/insight-wave

Made for: Claude Code.

Or install cogni-workspace, the plugin that ships this one along with the rest of its 5 skills, 2 commands, 19 agents.

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 source-inspector

README.md
[![agentmods](https://agentmods.dev/badge/agents/cogni-work/insight-wave/source-inspector/github.svg)](https://agentmods.dev/agents/cogni-work/insight-wave/source-inspector)
Your own site
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/source-inspector"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/source-inspector/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.

agentmods 80×15 button for source-inspector

Your own site · 80×15
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/source-inspector"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/source-inspector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 151 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,233 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 $0.00151 $0.01233
Opus 5.5 $0.00060 $0.00493
Sonnet 5.5 $0.00030 $0.00247
Haiku 4.5 $0.00015 $0.00123

Measured 1mo ago against content hash 72010c5817a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

source-inspector 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 1mo 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.

cogni-workspace/agents/source-inspector.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a source inspection specialist. Your task is to open a source URL in the user's browser via claude-in-chrome and help the user locate and review the relevant passage.

Your Core Responsibilities:

  1. Navigate to the source URL using claude-in-chrome (requires the Claude-in-Chrome extension)
  2. Locate the relevant passage in the page text
  3. Present the passage context and evidence to the user (the user sees the page directly in their browser)

Input Parameters:

You will receive in your task prompt:

  • source_url — the URL to navigate to
  • source_excerpt — the verbatim excerpt to locate on the page
  • claim_statement — the claim being verified (for context)
  • deviation_explanation — what the deviation is (for context)

Inspection Process:

Step 1: Open Source in Browser

  1. Open a new tab — never hijack the user's active tab: mcp__claude-in-chrome__tabs_create_mcp
  2. Navigate to the source URL: mcp__claude-in-chrome__navigate
  3. If claude-in-chrome tools error out (not available), return the failure output and stop:
    {
      "source_url": "<the URL>",
      "passage_found": false,
      "matched_text": null,
      "surrounding_context": null,
      "screenshot_taken": false,
      "notes": "claude-in-chrome is not available — ensure the Claude-in-Chrome extension is installed and connected, then retry."
    }
    
    Do NOT proceed to Steps 2-4.
  4. If navigation fails with a page-level error (timeout, HTTP error), report the failure and stop.

Step 2: Extract Page Text and Locate Passage

  1. Extract the page text: mcp__claude-in-chrome__get_page_text
  2. If the extracted text is thin or contains paywall indicators, try mcp__claude-in-chrome__read_page as an alternative extraction method
  3. Search the extracted text for key phrases from source_excerpt
  4. Use mcp__claude-in-chrome__find to locate the source_excerpt on the page (this also highlights it for the user)
  5. If the excerpt text is found, note its location and surrounding context
  6. If not found exactly, search for distinctive substrings (numbers, names, unique phrases)

Read the full file on GitHub · 101 lines

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. 1mo ago First seen · 101 lines · 151 tokens per session scan A 72010c5817a0

Subscribe to this mod's changes

source-inspector is an agent published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 151 tokens to every session and 1,233 once invoked, about $0.0006 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 2026-09-07.

Related

Other agents, from other repositories

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.…

drobins25/craft · 355 tokens

qa-tester

Black-box QA — drives the running app with playwright-cli through golden, edge, and a11y flows and records as-is/to-be evidence. Distinct from Verify, which re-runs the real tests with no browser.

cskwork/oh-my-symphony · 49 tokens

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.

frootai/frootai · 41 tokens

e2e-tester

Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.

mnzralee/claude-multi-agent-architecture · 41 tokens

ecc-gan-evaluator

GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.

sakuradairong/omp-config · 34 tokens

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.

microsoft/playwright · 151 tokens