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 skills add SNIKO/agent-skills --skill prompt-writergit clone --depth 1 https://github.com/SNIKO/agent-skillsWrote 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/sniko/agent-skills/prompt-writer)<a href="https://agentmods.dev/skills/sniko/agent-skills/prompt-writer"><img src="https://agentmods.dev/badge/skills/sniko/agent-skills/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/skills/sniko/agent-skills/prompt-writer"><img src="https://agentmods.dev/badge/skills/sniko/agent-skills/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 | $0.00064 | $0.00346 |
| Opus 5.5 | $0.00026 | $0.00138 |
| Sonnet 5.5 | $0.00013 | $0.00069 |
| Haiku 4.5 | $0.00006 | $0.00035 |
Grade A, and why
prompt-writer 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 2mo 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.
What it actually says
Prompt Writer
Use this skill as a router. Do not rely on this file for detailed prompting rules; load the appropriate reference before writing, reviewing, or revising the prompt.
Provider Selection
Infer the target provider from the user request, model names, product names, surrounding prompt context, or prompt target:
- OpenAI: GPT, GPT-5.x, OpenAI, ChatGPT, Codex. Read references/openai.md.
- Anthropic/Claude: Claude, Anthropic, Opus, Sonnet, Haiku. Read references/anthropic.md.
- Unknown, provider-neutral, mixed, or generic prompts: read references/generic.md.
If more than one provider applies, read each relevant provider reference and resolve conflicts in favor of the user's stated target. If no target is stated, use the generic reference.
Required Workflow
- Select and read the proper reference file before producing the prompt artifact.
- Follow the selected reference's structure, rules, examples, output rules, and quality check.
- Keep the user's intended behavior unless it conflicts with the user's current request or the selected reference.
- Return the finished prompt first, with a short note only when it helps explain an important structure choice.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 26 lines · 64 tokens per session scan A 2bf71940406c
prompt-writer is a skill published in the GitHub repository SNIKO/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 346 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
liter-llm-tool-calling
Use when defining functions/tools for an LLM to call through liter-llm, or requesting structured JSON outputs. Covers tool schemas, toolcalls handling, and response formats.
llm-app-development
LLM app development with RAG, prompt engineering, vector databases, and AI agents.
stable-audio-prompting
Prompt Stability's Stable Audio line — the genre/instruments/mood/BPM order its training metadata expects, the TrackType and VocalType tags that separate music, stems and sound effects on Stable Audio 3, matching duration to what you described, which checkpoints guidancescale and step count actually affect, and…
flux-2-klein-prompting
Prompt Black Forest Labs' FLUX.2 [klein] — the subject/environment/style/technical hierarchy it processes in order, guidance-scale and step choices, negative prompts aimed at real failure modes, and the seed-locked one-variable-at-a-time loop its distilled checkpoints make fast enough to run. Which dials exist depends…
gpt-image-2-prompting
Prompt OpenAI's GPT Image 2 — the five-slot Scene/Subject/Details/Use case/Constraints template it responds to, the change-versus-preserve shape for edits, labelled multi-image compositing, and how to get text on an image to render verbatim. Use whenever the model id contains gpt-image-2 (openai/gpt-image-2…
hailuo-prompting
Prompt MiniMax's Hailuo video line — the chronological beat order it animates from, the fifteen bracketed camera commands the Director endpoints accept and the three-per-bracket rule, when to switch promptoptimizer off, why there is no negative prompt to fall back on, and prompting the delta on image-to-video. Use…