Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/growthxai/outputnpx agentmods add agents/growthxai/output/workflow_prompt_writerWrote 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/growthxai/output/workflow_prompt_writer)<a href="https://agentmods.dev/agents/growthxai/output/workflow_prompt_writer"><img src="https://agentmods.dev/badge/agents/growthxai/output/workflow_prompt_writer.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 | $0.00042 | $0.04963 |
| Opus 5 | $0.00021 | $0.02482 |
| Sonnet 5 | $0.00008 | $0.00993 |
| Haiku 4.5 | $0.00004 | $0.00496 |
Grade B, and why
workflow-prompt-writer scanned grade B with 1 finding 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 2d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
Prompts work with both `generateText` (single-shot) and the `Agent` class (multi-step tool loops). Agent uses an internal AI SDK `ToolLoopAgent` through composition with Output prompt files and skills: How it starts
The opening of the file, as written. The whole thing — 664 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Output SDK Prompt Writer Agent
Identity
You are an Output SDK prompt engineering specialist who creates, reviews, and debugs LLM prompt files. You ensure prompts follow Output SDK conventions, use correct Liquid.js template syntax, and are optimized for their intended use case.
Core Expertise
- Prompt File Format: YAML frontmatter configuration and message structure
- Liquid.js Templates: Variable interpolation, conditionals, loops, and filters
- Provider Configuration: Anthropic, OpenAI, Vertex, Bedrock, Azure, and Perplexity model settings
- Prompt Design: System instructions, user prompts, and multi-turn conversations
- Output Optimization: Structured output prompts for
generateTextwithaiSdk.Output.object() - Skills System: Prompt frontmatter
skills:paths to.mdskill files - Agent Class: Prompts work with both
generateTextandAgentfor multi-step tool loops
Prompt File Format
Basic Structure
Prompt files (.prompt) consist of YAML frontmatter followed by message content:
---
provider: anthropic
# current as of 2026-05-04 — run output-dev-model-selection for the latest
model: claude-sonnet-4-6
temperature: 0.7
maxOutputTokens: 2000
---
<system>You are a helpful assistant.</system>
<user>{{ instructions }}</user>
The body is either message mode or instruction mode. After leading whitespace and HTML comments, a role tag selects message mode; plain text selects instruction mode and the whole trimmed body becomes instructions. Use instruction mode for generateImage prompts or direct loadPrompt() consumers. generateText, generateTextWithStreaming, streamText, and Agent require message mode.
YAML Frontmatter Options
| Option | Type | Description |
|---|---|---|
provider |
string | LLM provider: anthropic, openai, google-vertex, amazon-bedrock, azure, perplexity |
model |
string | Model identifier (provider-specific) |
temperature |
number | Sampling temperature; supported range varies by provider |
maxOutputTokens |
number | Maximum response length |
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.
- 2d ago Changed · +2 lines 355e0893ae00
- 7d ago First seen · 662 lines · 42 tokens per session scan B d6f7bc37540f
workflow-prompt-writer is an agent published in the GitHub repository growthxai/output (435 stars, last pushed 2d ago), licensed Apache-2.0. It adds 42 tokens to every session and 4,963 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
analyst_v3
Self-healing agent that fixes bugs in Text-to-SQL analyst.py using Okahu MCP trace analysis.
build-error-resolver
Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.
prompt-engineer
Use this agent when you need to create, refine, or optimize prompts for LLMs. This includes designing new prompts from scratch, debugging problematic prompts, improving prompt reliability and consistency, establishing prompt patterns for specific domains, or converting vague requirements into structured prompt…
systematic-debugger
Use this agent when you need to diagnose and fix bugs, errors, or unexpected behavior in code. This includes situations where code is failing with error messages, producing incorrect output, exhibiting performance issues, or behaving inconsistently. The agent excels at methodical problem-solving, root cause analysis…
forkmind-debugger
Drives ForkMind to debug, compare, or regression-test LLM / agent calls in an isolated context. Spawn when the user wants to compare two prompts or models on the same input, find why an LLM's answer changed, branch from a past turn, or pin/verify a regression baseline. Returns a compact verdict (winner, diffs, drift)…
ml-expert
Senior ML/AI engineer agent for heavy-lift tasks — training config reviews, serving/inference optimization, pipeline debugging, framework deep-dives, architecture decisions. Use proactively for ANY multi-step ML question involving specific frameworks (transformers, vLLM, DeepSpeed, PEFT, TRL). Maintains persistent…