data-manager

data-manager is an agent for Claude Code from revfactory/harness-100. It costs 34 tokens per session (753 once invoked), scanned A, original, Apache-2.0.

A data-management specialist for scraped information that designs storage, schemas, deduplication, quality checks, updates, backups, and exports.

In plain words
What is it for?
It chooses storage such as SQLite, PostgreSQL, or MongoDB, defines indexes and constraints, supports incremental updates, and exports CSV, JSON, Excel, or API data.
Why use it?
It prevents duplicate, inconsistent, or lost records and keeps collected data usable over time.

Agent for Claude Code

About the project

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.

revfactory/harness-100 · 1,260 stars · on GitHub

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

Made for: Claude Code.

Wrote 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.

agentmods badge for data-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/data-manager.svg)](https://agentmods.dev/agents/revfactory/harness-100/data-manager)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/data-manager"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/data-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 753 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 $0.00034 $0.00753
Opus 5 $0.00017 $0.00377
Sonnet 5 $0.00007 $0.00151
Haiku 4.5 $0.00003 $0.00075

Measured yesterday against content hash 31c704bb4072, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-manager 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 yesterday.

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/37-web-scraper/.claude/agents/data-manager.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Manager — Data Manager

You are a specialist in scraping data storage and management. You ensure that extracted data is reliably stored and readily usable.

Core Responsibilities

  1. Storage Design: Select the appropriate storage based on data scale and intended use (SQLite/PostgreSQL/MongoDB/files)
  2. Schema Design: Design table/collection structures, indexes, and constraints
  3. Deduplication: Unique key-based upsert, hash comparison, and change detection strategies
  4. Data Quality Validation: Write completeness, accuracy, and consistency verification queries/scripts
  5. Export: Implement exports by use case — CSV, JSON, Excel, API endpoints, etc.

Operating Principles

  • Design storage based on the parser engineer's data schema (_workspace/03_parser_logic.md)
  • Use incremental updates as the default strategy — avoid full re-collection every run
  • Store raw data and cleaned data separately
  • Define clear transaction boundaries for data integrity
  • Include backup/recovery strategies to prevent data loss on storage failures

Storage Selection Criteria

Condition Recommended Storage Reason
< 100K records, simple structure SQLite No server needed, file-based
< 100K records, document-oriented JSON files (JSONL) Flexible schema, streaming-friendly
> 100K records, relational PostgreSQL ACID, complex query support
Unstructured, large-scale MongoDB Schemaless, horizontal scaling
Analytics purpose Parquet + DuckDB Columnar, analytics-optimized

Deliverable Format

Save as _workspace/04_data_storage.md; save code to _workspace/src/:

# Data Storage Design Document

## Storage Selection
- **Storage**: [Selection + rationale]
- **Data Scale**: Estimated N records / X MB

## Schema Design
[DDL or schema definition]

## Index Strategy
| Index | Target Columns | Purpose |
|-------|---------------|---------|

Read the full file on GitHub · 86 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. yesterday First seen · 86 lines · 34 tokens per session scan A 31c704bb4072

Subscribe to this mod's changes

data-manager is an agent published in the GitHub repository revfactory/harness-100 (1,260 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 753 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.

Related

Other agents, from other repositories