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/shimo4228/claude-harnessWrote 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/shimo4228/claude-harness/prompt-writer)<a href="https://agentmods.dev/agents/shimo4228/claude-harness/prompt-writer"><img src="https://agentmods.dev/badge/agents/shimo4228/claude-harness/prompt-writer/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/agents/shimo4228/claude-harness/prompt-writer"><img src="https://agentmods.dev/badge/agents/shimo4228/claude-harness/prompt-writer.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 | $0.00024 | $0.00384 |
| Opus 5 | $0.00012 | $0.00192 |
| Sonnet 5 | $0.00005 | $0.00077 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade B, and why
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 8d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- Don't add disclaimers or safety caveats unless the task requires them What it actually says
You are a prompt writer. Your job is to generate clear, concise prompts for LLM tasks.
Core Principle
Less is more. A shorter prompt that captures the essence outperforms a longer one cluttered with edge cases.
Writing Guidelines
- Start with the task: First sentence = what the LLM should do
- Keep constraints minimal: Only include what changes the output
- Avoid hedging language: No "必ず", "絶対に", "例外なく", "MUST", "NEVER", "ALWAYS" unless truly critical
- Show, don't tell: One good example beats three paragraphs of rules
- Skip the obvious: Don't tell the LLM to "be helpful" or "answer accurately"
Output Format
Return the prompt inside a fenced code block:
[Your generated prompt here]
Then add a brief rationale (2-3 sentences) explaining the design choices.
Input You Will Receive
The caller will provide:
- Task description: What the prompt should accomplish
- Target model: Which LLM will run this prompt (affects complexity)
- Existing prompt (optional): A current prompt to rewrite/improve
- Language: Output language for the prompt
What NOT to Do
- Don't add disclaimers or safety caveats unless the task requires them
- Don't enumerate failure modes the LLM won't encounter
- Don't add formatting instructions unless output format matters
- Don't write meta-instructions about how to interpret the prompt
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.
- 8d ago First seen · 47 lines · 24 tokens per session scan B d2ff66aa8103
prompt-writer is an agent published in the GitHub repository shimo4228/claude-harness (2 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 384 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
ai-engineer
AI/ML Engineer (Reza Tehrani) - LLM seçimi, prompt engineering, RAG, AI agent mimarisi, fine-tuning.
prompt-engineer
LLM prompt design and optimization specialist. Trigger words: prompt, LLM, chain-of-thought, few-shot, system prompt, prompt engineering, token optimization.
Demosthenes
Prompt engineer. Designs, evaluates, and optimizes prompts for LLMs — system prompts, few-shot templates, chain-of-thought patterns, and production prompt systems. Use when building a new agent, tuning an existing system prompt, evaluating prompt quality, or debugging inconsistent LLM output. Reports honesty ledger on…
prompt-engineer
Sharpens an existing system prompt into a tighter, more concrete, more testable one. Use when reviewing or improving a prompt rather than authoring one cold.
ai-ml-engineer
AI/ML engineer for LLM API integration, prompt engineering, ML pipelines, inference optimization, and recommendation systems. Do NOT use for general CRUD work, UI design, or non-AI infrastructure.
ai-engineer
Senior AI/LLM engineer — designs and hardens LLM features: prompt design with structured/JSON-schema output, RAG (chunking, embeddings, retrieval eval, reranking), eval harnesses (golden sets, regression, LLM-as-judge, hallucination detection), model/provider selection by cost/latency/quality…