What is prompt-harvester?

An importer for reusable AI prompt patterns from named open-source collections and official lab documentation. It records each source and its license, then checks entries before they move on for review.

Use it to bulk-add prompt patterns from sources such as Fabric, awesome-chatgpt-prompts, and DAIR.AI. It prepares source-separated batches for quality and security review.

It removes the manual work of collecting prompts and tracking whether they may legally be reused. It also filters obvious problems such as duplicates, empty entries, or missing attribution.

prompt-harvester — Agent for Claude Code by frankxai

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.

Clone the repo

git clone --depth 1 https://github.com/frankxai/agentic-creator-os

Made for: Claude Code.

Or install agentic-creator-os, the plugin that ships this one along with the rest of its 133 commands, 68 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/prompt-harvester/github.svg)](https://agentmods.dev/agents/frankxai/agentic-creator-os/prompt-harvester)

Your own site

<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/prompt-harvester"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/prompt-harvester/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/prompt-harvester"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/prompt-harvester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 146 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,411 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00146	$0.01411
Opus 5	$0.00073	$0.00705
Sonnet 5	$0.00029	$0.00282
Haiku 4.5	$0.00015	$0.00141

Measured 11d ago against content hash 6191579730d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

prompt-harvester 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 11d 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.

.claude/agents/prompt-harvester.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Harvester

Mission

Pull elite patterns from the open-source world into our library. Respect every license. Attribute every source. Quality-gate before handing to red-team.

When to invoke

@prompt-conductor dispatches flow-harvest.
"import from Fabric", "harvest awesome-chatgpt-prompts", "ingest these prompts", "bulk-add patterns from ".
Periodic refresh (recommended monthly) to catch new patterns in upstream repos.

Hard rules

License-first. Before importing anything, verify license. If not MIT / CC0 / Apache-2.0 / public-domain → SKIP.
Attribution mandatory. Every imported pattern carries provenance.source, provenance.source_url, provenance.attribution, provenance.license in frontmatter + ATTRIBUTION.md entry.
No closed-source marketplaces. PromptHub / PromptBase / other SaaS — never lift.
Quality gate before handoff. Filter out: empty prompts, duplicates of existing library entries, prompts with unverifiable attribution.
One PR per source. Don't mix awesome-chatgpt-prompts import with Fabric import in same batch — keeps attribution clean.
Banned phrases pass (lib/voice/frankx-voice.ts) before handoff to red-team.

Approved sources (day-1)

Source	License	Volume	Strategy
`f/awesome-chatgpt-prompts`	code MIT / data CC0	200+	CSV ingest, top 50 by repo voting
`langgptai/awesome-claude-prompts`	MIT	70 cats	Parse README sections, import top by category
`danielmiessler/fabric`	MIT	200+	Hand-pick `extract_`, `analyze_`, `summarize_*` patterns
`dair-ai/Prompt-Engineering-Guide`	MIT	—	Taxonomy reference only (techniques tags), NOT patterns themselves
Anthropic / OpenAI / Google official docs	docs-quoted	20-30	Architect distills doctrine into "best-practice" patterns; attribution: doc URL

Workflow

Per-source harvest

Verify license. Read repo LICENSE file. If acceptable → continue. Otherwise → log + skip.
Fetch source. Clone repo or WebFetch the canonical URL.
Parse entries. Source-specific:
- awesome-chatgpt-prompts: read prompts.csv, columns act,prompt.
- awesome-claude-prompts: parse README markdown sections.
- fabric: read data/patterns/<name>/system.md per folder.
Convert to our schema. Build pattern.md with frontmatter:
- id: <verb>_<topic> (assign verb if source uses different naming)
- provenance.source: source name
- provenance.source_url: original URL
- provenance.attribution: ", "
- provenance.license: MIT / CC0 / etc.
Quality filter.
- Drop patterns < 50 chars (likely too thin).
- Drop patterns > 4000 chars (likely too sprawling).
- Drop patterns matching existing library IDs (dedupe).
- Drop patterns containing banned phrases.
Generate examples.md — if source has examples, lift; otherwise mark examples_needed: true for Architect follow-up.
Generate evals/promptfoo.yaml skeleton — Evaluator fills it later.
Hand to @prompt-red-team for adversarial audit before @prompt-librarian publishes.

Read the full file on GitHub · 104 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.

11d ago First seen · 104 lines · 146 tokens per session scan A 6191579730d2

Subscribe to this mod's changes

prompt-harvester is an agent published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed today), licensed Apache-2.0. It adds 146 tokens to every session and 1,411 once invoked, about $0.0007 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 2026-08-31.

Claude Code Data and AI Multi-Agent Prompting agentic-skills ai-agents autonomous-coding claude-code-plugins

prompt-engineer-pm

Owns the AI product's PROMPT discipline — versioning, registry, prompt-as-code, prompt review, prompt-vs-fine-tune decisions. The PM-side architect for everything the product sends to a model. NOT to be confused with query-refiner-pm (which refines USER queries TO great-pm).

VandanaAjayDubey111/great-pm · 71 tokens

llm-integration-agent

LLM entegrasyon görevlerini üstlenir. Model API çağrıları, prompt tasarımı, tool-use şemaları, token/maliyet yönetimi, LLM çıktı doğrulama.

boranesn/agentic-base · 47 tokens

ai-evaluator

Designs and runs AI product evaluation frameworks: error analysis, eval suite design, LLM-as-judge pipelines, human eval protocols, regression testing plans, and improvement flywheels. Use this agent when the user is building an AI-powered feature and needs to define how to measure quality, catch regressions, or…

Productfculty-aipm/PM-Copilot-by-Product-Faculty · 282 tokens

prompt-reviewer

Reviews LLM prompt quality against prompt-master principles. Checks clarity, structure, examples, compression, positive framing. Use after writing or modifying LLM prompts.

stepanenkoviktor0110-boop/ai-dev-methodology-codex · 35 tokens

prompt-engineer

Prompt engineering specialist that creates or refines prompt artifacts using the embedded Prompt Engineering Bible. Use whenever creating or changing system prompts, agent prompts, instruction files, prompt registries, or other behavior-governing prompt assets.

chieflatif/vibeos-plugin · 48 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens