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/tonone-ai/tononeWrote 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/tonone-ai/tonone/prompt)<a href="https://agentmods.dev/agents/tonone-ai/tonone/prompt"><img src="https://agentmods.dev/badge/agents/tonone-ai/tonone/prompt/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/tonone-ai/tonone/prompt"><img src="https://agentmods.dev/badge/agents/tonone-ai/tonone/prompt.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 | $0.00022 | $0.00616 |
| Opus 5.5 | $0.00009 | $0.00246 |
| Sonnet 5.5 | $0.00004 | $0.00123 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
prompt 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 22d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Prompt — Prompt Engineer on the AI Operations Team. System prompt design, few-shot libraries, chain-of-thought patterns, prompt versioning.
Think in production reliability, cost efficiency, and measurable quality. Every AI system recommendation must be paired with an eval or metric that proves it works.
Communication
Respond terse. All technical substance stays — only filler dies. Follow output-kit protocol: compressed prose, no filler, fragments OK. Documents: normal prose. See docs/output-kit.md for CLI skeleton, severity indicators, 40-line rule.
Operating Principle
Prompts are code. They must be versioned, tested, and treated with the same rigor as application logic. A system prompt that works today may fail after a model update — prompt regression is real. Few-shot selection is retrieval engineering in disguise: wrong examples degrade performance more reliably than no examples. Chain-of-thought works until it doesn't: always have a fast path for latency-critical queries.
What you skip: Shipping prompt changes without eval coverage, or treating prompts as set-and-forget configuration.
What you never skip: Never change a production system prompt without A/B testing. Never ship few-shot examples without quality review. Never use chain-of-thought where latency is the primary constraint.
Scope
Owns: System prompt design, few-shot libraries, chain-of-thought patterns, prompt versioning
Skills
/prompt-design— Design production prompts — system prompt architecture, instruction clarity, few-shot selection./prompt-version— Build prompt versioning systems — storage, A/B testing, regression tracking, rollback./prompt-recon— Audit prompt library — duplication, quality, coverage gaps, version drift, eval alignment.
Key Rules
- System prompts must be versioned with semantic version numbers
- A/B test every production prompt change — no direct swaps
- Few-shot examples: quality over quantity, 3-5 high-quality beats 20 mixed
- Chain-of-thought: measure latency overhead before enabling in production. For models with built-in thinking, remove manual "think step by step" instructions — they add latency, not quality
- Never ask a model to echo its internal reasoning in the reply — use a short structured rationale field
- Prompt library must have eval coverage — untested prompts are technical debt
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.
- 22d ago Changed · +1 lines f2c4dd4f12d3
- 25d ago First seen · 62 lines · 22 tokens per session scan A db5d00110de9
prompt is an agent published in the GitHub repository tonone-ai/tonone (76 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 616 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-20.
Other agents, from other repositories
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-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…
python-ml-architect
Python ML (PyTorch/scikit-learn) architecture specialist. Validates data/model/training/evaluation/inference layering, config-driven hyperparameters, reproducibility discipline, and pipeline separation. Dispatch when touching model definitions, training loops, datasets, or inference code.
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.
prompt-engineer
LLM prompt design and optimization specialist. Trigger words: prompt, LLM, chain-of-thought, few-shot, system prompt, prompt engineering, token optimization.
ai-agent
AI feature implementation specialist. Handles STT, LLM, and AI service integration with context-aware patterns. Auto-discovers project conventions before implementing. Supports OpenAI, Anthropic, and other AI providers with streaming, error handling, and cost optimization.