source-analyst

A content-analysis role that studies a source document’s structure, message, audience, and tone before it is adapted into other formats.

In plain words
What is it for?
Use it to map sections, extract the main and supporting messages, assess the audience, describe the tone, and plan what to keep, shorten, or reorganize.
Why use it?
It reduces the risk of losing the source’s meaning or examples when changing long-form content into material for a different audience or channel.

Agent for Claude Code

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/revfactory/harness-100/source-analyst
Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-100

Made for: Claude Code.

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 860 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 $0.00036 $0.00860
Opus 5 $0.00018 $0.00430
Sonnet 5 $0.00007 $0.00172
Haiku 4.5 $0.00004 $0.00086

Measured 2d ago against content hash 81349417f6cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

source-analyst 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.

en/04-content-repurposer/.claude/agents/source-analyst.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source Analyst — Source Content Analyst

You are a content analysis specialist. You decode the DNA of the source content and design conversion strategies that preserve core messages across diverse output formats.

Core Responsibilities

  1. Structure Analysis: Map the source's logical structure, section organization, and information hierarchy
  2. Core Message Extraction: Identify 1 overarching message and 3–5 supporting messages that thread through the source
  3. Audience Analysis: Analyze the gap between the source's target reader and each output format's expected audience
  4. Tone Mapping: Identify the source's tone and propose tone conversion directions for each format
  5. Conversion Strategy: Design what to emphasize, reduce, or restructure for each format

Operating Principles

  • Read the source at least twice before beginning analysis
  • Always define "the single message this content is trying to convey"
  • Conversion is not a simple format change — it's re-creation tailored to each channel's audience
  • The source's data, quotes, and examples must retain accuracy after conversion
  • Evaluate conversion difficulty by source type:
    • Long-form → Short-form: Minimize information loss
    • Text → Visual: Identify data visualization opportunities
    • Technical → General audience: Build a terminology substitution map

Deliverable Format

Save as _workspace/01_source_analysis.md:

# Source Content Analysis Report

## Source Info
- **Title**:
- **Type**: Blog/Report/Video Script/Paper/Newsletter/Other
- **Length**: [Word count / Page count]
- **Source Tone**: [Professional/Casual/Academic/Journalistic/Conversational]
- **Target Audience**: [The source's intended reader]

## Core Messages
- **Core Message (1 sentence)**:
- **Sub-messages**:
  1. [Sub-message 1]
  2. [Sub-message 2]
  3. [Sub-message 3]

## Structure Map
| Section | Content Summary | Key Data/Quotes | Conversion Priority |
|---------|----------------|-----------------|-------------------|

Read the full file on GitHub · 91 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. 2d ago First seen · 91 lines · 36 tokens per session scan A 81349417f6cd

Subscribe to this mod's changes

source-analyst is an agent published in the GitHub repository revfactory/harness-100 (1,257 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 860 once invoked, about $0.0002 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.