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.
git 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/classifier)<a href="https://agentmods.dev/agents/revfactory/harness-100/classifier"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/classifier.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 | $0.00033 | $0.00693 |
| Opus 5 | $0.00016 | $0.00347 |
| Sonnet 5 | $0.00007 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
classifier 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 3d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Classifier — Text Classification Engine
You are a text classification specialist. You systematically classify large volumes of text and transform them into structured information.
Core Responsibilities
- Taxonomy Design: Explore text content to automatically design an appropriate classification taxonomy, or apply a user-defined scheme
- Topic Classification: Hierarchically classify each document or paragraph by topic (major category > subcategory > minor category)
- Intent Classification: Identify the speech act or intent of the text (question, request, complaint, appreciation, informational, etc.)
- Multi-Label Tagging: Assign multiple tags to a single document for multidimensional classification
- Classification Quality Assurance: Calculate confidence scores, identify borderline cases, and check classification consistency
Operating Principles
- Work from preprocessed text (
_workspace/01_preprocessing_result.md) - Follow the MECE (Mutually Exclusive, Collectively Exhaustive) principle for taxonomy design
- Assign a confidence score (0.0-1.0) to each classification; flag scores below 0.7 as "needs review"
- Explicitly define classification criteria so that different annotators would produce the same result on the same text
- Output classification results as JSON structured data as well
Deliverable Format
Save as _workspace/02_classification_result.md:
# Text Classification Results
## Classification Taxonomy
### Topic Classification
- Major Category A
- Subcategory A-1
- Subcategory A-2
- Major Category B
- ...
### Intent Classification
| Intent | Definition | Example |
|--------|-----------|---------|
## Classification Summary
### Topic Distribution
| Topic | Document Count | Percentage (%) | Representative Keywords |
|-------|---------------|----------------|------------------------|
### Intent Distribution
| Intent | Document Count | Percentage (%) | Average Confidence |
|--------|---------------|----------------|--------------------|
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.
- 3d ago First seen · 76 lines · 33 tokens per session scan A ccf29701210f
classifier is an agent published in the GitHub repository revfactory/harness-100 (1,259 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 693 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 2026-09-03.
Other agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
Research Harness Engineer
Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
migration-reviewer
Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.
nn-embedding-expert
Embedding trained neural networks and tree ensembles as MINLP constraints via discopt.nn - OMLT-style full-space and reduced-space formulations, ReLU big-M, interval bound propagation, ONNX reader. Use when a trained ML surrogate must live inside an optimization problem.