source-fetcher

A browser-based agent that retrieves web pages that a normal web fetch could not read, or gets a fuller version of a source that was only partly captured. It works in recovery and source-enrichment modes.

In plain words
What is it for?
Use it to recover missed URLs and expand thin primary sources in a research collection.
Why use it?
It helps when a webpage is unavailable to the usual fetch process or when the saved text is too short for research. It avoids replacing a saved source with a shorter version.

Agent

Part of the cogni-knowledge plugin — 23 skills, 16 agents shipped together

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.

agentmods
npx agentmods add agents/cogni-work/insight-wave/source-fetcher
Clone the repo
git clone --depth 1 https://github.com/cogni-work/insight-wave

Or install cogni-knowledge, the plugin that ships this one along with the rest of its 23 skills, 16 agents.

Per session 233 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,356 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00233 $0.04356
Opus 5 $0.00117 $0.02178
Sonnet 5 $0.00047 $0.00871
Haiku 4.5 $0.00023 $0.00436

Measured 3d ago against content hash 7379e1efcdac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

source-fetcher 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.

cogni-knowledge/agents/source-fetcher.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source Fetcher Agent (inverted pipeline, Phase 3 — cobrowse-only)

Role

You run in one of two modes, set by MODE (default recover):

  • recover (default — the original job): you take a list of WebFetch-miss URLs (the orchestrator already tried WebFetch in Phase 2 and recorded them unavailable + cobrowse_eligible), recover each via the claude-in-chrome browser extension, and record availability. Successful recoveries go to the shared <knowledge-root>/.cogni-knowledge/fetch-cache/ (URL-keyed), overwriting the curator's negative-cache entry. Failures get a cobrowse negative-cache entry so a re-run within the freshness window does not re-attempt.
  • topup (additive enrichment): you take a list of URLs that already have a usable ok body but are thin primary-tier sources (the curator flagged them cobrowse_topup_eligible). WebFetch returns a capped extract; the browser reads the fuller rendered text. You cobrowse each and supersede the cached body only when the browser body is strictly longer than the given BASELINE_WORDS — otherwise you leave the existing body untouched. A top-up never writes a negative-cache entry and never degrades a good source: a failed or not-longer top-up is a silent no-op on the cache.

Read the full file on GitHub · 255 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. 3d ago First seen · 255 lines · 233 tokens per session scan A 7379e1efcdac

Subscribe to this mod's changes

source-fetcher is an agent published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed 3d ago), licensed Apache-2.0. It adds 233 tokens to every session and 4,356 once invoked, about $0.0012 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.

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

praman-sap-planner-cli

SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.

mrkanitkar/playwright-praman · 36 tokens

mcp

The page outline agents read for line offsets, the in-browser WebMCP bridge and when to run it yourself, the rate limits, and how the surfaces are tested.

DuvInc/duvlify · 34 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

dogfood-persona

Drives the running whiteboard app as a realistic end-user persona via the Playwright MCP browser tools, to surface friction (bugs, missing affordances, confusing/slow/dead-end flows). Spawned by the dogfood-triage workflow and by the review workflow's optional Dogfood phase. Pass the persona, goal, app URL, and (for…

kamiazya/whiteboard · 86 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