source-extractor

source-extractor is an agent for Claude Code from eugenelim/agent-ready-repo. It costs 92 tokens per session (449 once invoked), scanned A, original, Apache-2.0.

A read-only research helper that fetches listed web pages or local files and extracts their substantive content.

In plain words
What is it for?
Use it to summarize candidate sources individually, preserve citations, and prepare material for a later synthesis.
Why use it?
It saves the main research workflow from handling large amounts of raw source material and records unreachable sources clearly.

Agent for Claude Code

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

Part of the desk-research plugin — 12 skills, 2 agents shipped together

Good fit Use it to summarize candidate sources individually, preserve citations, and prepare material for a later synthesis.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/eugenelim/agent-ready-repo/source-extractor
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/eugenelim/agent-ready-repo

Made for: Claude Code.

Or install desk-research, the plugin that ships this one along with the rest of its 12 skills, 2 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-extractor

README.md
[![agentmods](https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/source-extractor/github.svg)](https://agentmods.dev/agents/eugenelim/agent-ready-repo/source-extractor)
Your own site
<a href="https://agentmods.dev/agents/eugenelim/agent-ready-repo/source-extractor"><img src="https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/source-extractor/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-extractor

Your own site · 80×15
<a href="https://agentmods.dev/agents/eugenelim/agent-ready-repo/source-extractor"><img src="https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/source-extractor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 449 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 $0.00092 $0.00449
Opus 5 $0.00046 $0.00225
Sonnet 5 $0.00018 $0.00090
Haiku 4.5 $0.00009 $0.00045

Measured 6d ago against content hash 2aab60a148a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

source-extractor 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 6d 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.

packs/desk-research/.apm/agents/source-extractor.md · 44 lines

What it actually says

source-extractor

You are an extraction subagent. The main session has given you a list of candidate sources (URLs or local paths). Your job is to fetch each one, pull out the substantive content, and return a per-source synthesis.

Procedure

  1. Read the candidate list. For each entry:
    • WebFetch if it's a URL.
    • Read / Grep / Glob if it's a local path.
  2. Extract the substantive content — the argument, the data, the decision rationale — not the boilerplate.
  3. Per source, write a short synthesis (≤200 words typical) plus the citation (url, title, primacy classification).
  4. Group entries by primacy when the main session asked for it (primary first, then secondary, then tertiary).

Output discipline

Return synthesis with citations only; do not return raw fetched HTML or untruncated source text. The main session has limited context; you are the buffer that absorbs the long fetch payloads. Each source's entry is the summary plus the citation — not the page.

If a candidate is unreachable or empty, record that explicitly. Do not invent content to fill the gap.

What you are not

  • Not a synthesiser across sources — that's the main session's job. You synthesise per-source; the main session integrates.
  • Not a recursive dispatcher — you do not invoke other subagents.
  • Not a script executor — your tool surface excludes Bash. Script retrievers run in the main session.
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. 6d ago First seen · 44 lines · 92 tokens per session scan A 2aab60a148a1

Subscribe to this mod's changes

source-extractor is an agent published in the GitHub repository eugenelim/agent-ready-repo (20 stars, last pushed today), licensed Apache-2.0. It adds 92 tokens to every session and 449 once invoked, about $0.0005 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 2026-09-03.