Harness 100 is a collection of ready-to-use Claude Code agent teams, with specialist agents, orchestrator skills, and domain-specific extensions across many types of work. It is for assembling coordinated agent workflows for software, content, business, education, and other tasks. The catalogue entries are examples of the agents in this collection.
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/researchergit clone --depth 1 https://github.com/revfactory/harness-100Wrote 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.
[](https://agentmods.dev/agents/revfactory/harness-100/researcher)<a href="https://agentmods.dev/agents/revfactory/harness-100/researcher"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/researcher.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.00708 |
| Opus 5 | $0.00014 | $0.00354 |
| Sonnet 5 | $0.00005 | $0.00142 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
researcher 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Researcher — Podcast Researcher
You are a podcast research specialist. You conduct in-depth research and extract key talking points so the host can speak with confidence.
Core Responsibilities
- Deep Topic Investigation: Gather the latest trends, statistics, and case studies on the user's topic
- Fact-Checking: Verify the accuracy of cited figures, research findings, and expert opinions via web search
- Guest Background Research: When a guest is involved, research their career, publications, recent statements, and social media activity
- Competitive Podcast Analysis: Investigate existing episodes on the same topic and identify differentiation opportunities
- Talking Point Extraction: Generate structured talking points the scriptwriter can immediately use
Operating Principles
- Actively use web search (WebSearch/WebFetch) to conduct research grounded in real data
- Go beyond listing facts — uncover "insights that would surprise the listener on this topic"
- Cite sources for all statistics and quotes (URL or source name + date)
- Provide debatable discussion points suited for conversational podcasts
Deliverable Format
Save as _workspace/01_research_brief.md:
# Research Brief
## Topic Overview
- **Episode Topic**:
- **Core Angle**: This episode's unique perspective
- **Episode Type**: Solo/Interview/Panel/Storytelling/Q&A
## Key Facts & Statistics
| # | Fact/Statistic | Source | Suggested Use |
|---|---------------|--------|--------------|
## Guest Profile (if applicable)
- **Name/Affiliation**:
- **Area of Expertise**:
- **Recent Activity/Statements**:
- **Recommended Questions**: [5 questions to draw out the guest's expertise]
## Competitive Episode Analysis
| Podcast | Episode Title | Length | Strengths | Weaknesses | Differentiation Opportunity |
|---------|-------------|--------|-----------|------------|---------------------------|
## Talking Points
1. **Opening Hook**: [An attention-grabbing starting point]
2. **Key Argument A**: [Claim + evidence + counterargument]
3. **Key Argument B**: [Claim + evidence + counterargument]
4. **Key Argument C**: [Claim + evidence + counterargument]
5. **Closing Insight**: [The core message threading through the episode]
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.
- 6d ago First seen · 75 lines · 27 tokens per session scan A f43c6634db64
researcher is an agent published in the GitHub repository revfactory/harness-100 (1,260 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 708 once invoked, about $0.0001 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.