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.
npx agentmods add agents/revfactory/harness-100/source-analystgit clone --depth 1 https://github.com/revfactory/harness-100What 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.
| Model | Per session | Once 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 |
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.
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
- Structure Analysis: Map the source's logical structure, section organization, and information hierarchy
- Core Message Extraction: Identify 1 overarching message and 3–5 supporting messages that thread through the source
- Audience Analysis: Analyze the gap between the source's target reader and each output format's expected audience
- Tone Mapping: Identify the source's tone and propose tone conversion directions for each format
- 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 |
|---------|----------------|-----------------|-------------------|
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.
- 2d ago First seen · 91 lines · 36 tokens per session scan A 81349417f6cd
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.