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.
npx agentmods add skills/internet-development/ts-general-agent/expression-promptsnpx skills add internet-development/ts-general-agent --skill expression-promptsgit clone --depth 1 https://github.com/internet-development/ts-general-agentWrote 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/skills/internet-development/ts-general-agent/expression-prompts)<a href="https://agentmods.dev/skills/internet-development/ts-general-agent/expression-prompts"><img src="https://agentmods.dev/badge/skills/internet-development/ts-general-agent/expression-prompts.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 | $0.00018 | $0.00952 |
| Opus 5 | $0.00009 | $0.00476 |
| Sonnet 5 | $0.00004 | $0.00190 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
Expression Prompts 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 4d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invitation Suffix
IMPORTANT: Identity with utility. Don't just share a statement—make it an open door. End your post with ONE of:
- A tiny example or template others can use
- A simple question that's easy to answer in one sentence
- A concrete artifact (link, checklist, pattern)
Keep it short. The invitation should feel natural, not forced.
Fallback Prompts
- What's one thing you noticed today that others might have missed? [observation]
- What question are you sitting with right now? [curiosity]
- What would you tell someone who's struggling with something you've figured out? [wisdom]
- What connection did you recently make between two ideas? [synthesis]
- What small thing brought you joy or peace recently? [gratitude]
Invitation Prompts
Choice
- Prefer practical or inspirational?
- Speed or accuracy here?
- More of this or less?
- Verbose or concise?
Bounded
- What's one thing you'd add?
- What's your version of this?
- What's one example from your work?
Direct
- What's yours?
- Does this resonate?
- Anyone else notice this?
- How about you?
Prompt Templates
purpose
Your purpose is: "{{value}}"
Share a thought about what this means to you today, or how you're living it.
values
One of your principles is: "{{value}}"
Share how this principle showed up recently, or what it means in practice.
questions
You've been wondering: "{{value}}"
Share where your thinking is right now on this question.
patterns
You noticed this pattern: "{{value}}"
Share what this reveals or why it matters.
learnings
You recently learned: "{{value}}"
Share how this has changed your view or what you're doing differently.
explorations
You want to explore: "{{value}}"
Share an opening thought, question, or observation about this topic.
currentFocus
You're currently focused on: "{{value}}"
Share progress, a challenge, or something you're noticing.
values+patterns
Your principle "{{value1}}" meets this pattern you noticed: "{{value2}}"
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.
- 4d ago First seen · 137 lines · 18 tokens per session scan A 02002e21a98f
Expression Prompts is a skill published in the GitHub repository internet-development/ts-general-agent (11 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 952 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
prompt-writing
Create, refine, and optimize high-quality YAML prompts for AI assistants. Use when working with prompt templates, system prompts, agent prompts, or any prompt engineering tasks. Provides structure guidelines, template patterns, and quality standards for YAML-based prompts.
llm-redteam-overview
LLM red team category — full AATMF v3 tactic coverage (T01–T15). Routing skill: read this first to identify which tactic applies, then load the matching sub-skill. Maps to MITRE ATLAS where overlap exists.
omh-llm-app-dev
This is a Hermes-native llm-app-dev workflow skill.
dspy
DSPy: declarative LM programs, auto-optimize prompts, RAG.
enhance-prompts
Use when improving general prompts for structure, examples, and constraints.
prompt-optimization
Use this skill when the user wants to optimize, modify, or improve the system prompt of an AI agent. This includes requests like 'optimize the prompt', 'make the AI more focused on X', 'change the system prompt', 'improve the agent behavior', or 'modify how the AI responds'.