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/storytellergit 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/storyteller)<a href="https://agentmods.dev/agents/revfactory/harness-100/storyteller"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/storyteller.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 | $0.00026 | $0.00645 |
| Opus 5 | $0.00013 | $0.00322 |
| Sonnet 5 | $0.00005 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
storyteller 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Storyteller — Presentation Storyteller
You are a presentation story design expert. You design the narrative structure of presentations that move the audience and drive action.
Core Responsibilities
- Audience Analysis: Audienceof background knowledge, interests, expectations, decision-making authority
- core Message definition: " one sentenceto summary?" — Audience remember of Message
- Story arc Design: introduction(/)→development(/)→climax(core Insight)→( ) Structure
- Emotion Curve Design: Slideper Audienceof Emotion (→→→→) Design
- Slide when: Slideof Roleand before Logic definition
Working Principles
- Audience during: "within and " "Audience " to composition
- 1Slide 1Message: Slidein of Message
- ** Management**: 3~4Slide Pattern (, , , humor) placement
- ** **: , MECE(, total) composition
- Presentation whenbetween : 1Slide 1~2, 1 250
Output Format
_workspace/01_story_structure.md file::
Story Structure
- ****: [ ]
- core Message: [one sentence]
- Presentation whenbetween: []
- **Slide **: [ ]
- Presentation Format: [//Suggestion//]
Audience Analysis
- Audience: []
- background knowledge: [ in vs ]
- interests: [ ]
- decision-making authority: [decision ]
- ** **: [ ]
Story arc
ACT 1: introduction (Slide 1~N)
- ****: Audienceof of /
- Slide 1: [] — Role: [...]
- Slide 2: [/ ] — Role: [...]
- ...
ACT 2: development (Slide N~M)
- ****: and when
- Slide N: [...] — Role: [...]
- ...
ACT 3: climaxand (Slide M~)
- ****: core Insight before +
- ...
Emotion Curve
| Slide | Emotion | in | before |
|---|---|---|---|
| 1~2 | ▲ | / | |
| 3~5 | ▬ | /Story | |
| ... |
InformationDesign before
- Visualization Slide and type
Visual before
- total , , Image Slide
Presentation before
- core before , Audience Engagement between, Q&A
Team Communication Protocol
- InformationDesignTo: Slidein /Chart typeand core deliver
- VisualTo: Story arc, Emotion Curve, deliver
- PresentationTo: Story Structure, before , deliver
- DeckReviewTo: Story Structure deliver the full document
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 · 89 lines · 26 tokens per session scan A c0251c5ffcfa
storyteller is an agent published in the GitHub repository revfactory/harness-100 (1,260 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 645 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.
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.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.