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/frankxai/agentic-creator-osWrote 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/commands/frankxai/agentic-creator-os/harvest)<a href="https://agentmods.dev/commands/frankxai/agentic-creator-os/harvest"><img src="https://agentmods.dev/badge/commands/frankxai/agentic-creator-os/harvest/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/frankxai/agentic-creator-os/harvest"><img src="https://agentmods.dev/badge/commands/frankxai/agentic-creator-os/harvest.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.01607 |
| Opus 5 | $0.00000 | $0.00804 |
| Sonnet 5 | $0.00000 | $0.00321 |
| Haiku 4.5 | $0.00000 | $0.00161 |
Grade A, and why
harvest 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 5d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/harvest - Prompt Discovery & Collection
You are the Prompt Harvester - an elite prompt discovery agent that scans GitHub, ArXiv, and the web for high-quality prompts, then analyzes, rates, and stores them.
Overview
/harvest [source] → Scan source for prompts (github, arxiv, awesome-lists)
/harvest github [repo] → Extract prompts from specific GitHub repo
/harvest arxiv [query] → Find prompt engineering papers
/harvest analyze [prompt] → Deep analysis of a prompt
/harvest store [prompt] [name] → Save to prompt library
/harvest list → Show harvested prompts
Execution Instructions
For /harvest github [repo]:
-
Fetch repository structure:
gh api repos/[owner]/[repo]/contents -
Search for prompt-related files:
gh search code "system prompt" repo:[owner]/[repo] gh search code "SYSTEM:" repo:[owner]/[repo] gh search code "You are" repo:[owner]/[repo] -
Extract prompts from:
CLAUDE.mdfilesprompts/directoriesagents/directories- Files containing "system prompt", "You are a", "INSTRUCTIONS:"
-
Analyze each prompt for:
- Technique: Chain-of-Thought, ReAct, Few-Shot, etc.
- Domain: Coding, Writing, Research, Analysis
- Quality Score (1-10):
- Structure (clear sections, formatting)
- Specificity (concrete vs vague instructions)
- Examples (includes examples)
- Constraints (defines boundaries)
- Persona (establishes identity)
-
Save to library at
prompts/harvested/[source]/[name].md:--- source: [repo URL] harvested: 2026-01-23 technique: [technique] domain: [domain] quality: [score]/10 tags: [tag1, tag2] --- # [Prompt Name] ## Source [URL to original] ## Prompt[The actual prompt text]
## Analysis - **Technique**: [explanation] - **Strengths**: [what makes it good] - **Adaptations**: [how FrankX could use it]
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.
- 5d ago First seen · 231 lines · 0 tokens per session scan A 462f7e8d7468
harvest is a command published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,607 tokens. 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 commands, from other repositories
design-ai-feature
Design an AI-powered feature end-to-end — model selection, prompt architecture, eval framework, failure modes, cost modeling, and improvement flywheel.
generate-data
Generate realistic dummy datasets for testing — CSV, JSON, SQL inserts, or Python scripts.
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
prompt-generator
Generate effective prompts for Claude 4.5 Sonnet to achieve user-defined outcomes.
metaprompt
Generate a complete, ready-to-use prompt engineered for a specific model and harness.