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 Londeren/claude-plugins --skill prompt-writergit clone --depth 1 https://github.com/Londeren/claude-pluginsWrote 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/londeren/claude-plugins/prompt-writer)<a href="https://agentmods.dev/skills/londeren/claude-plugins/prompt-writer"><img src="https://agentmods.dev/badge/skills/londeren/claude-plugins/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/londeren/claude-plugins/prompt-writer"><img src="https://agentmods.dev/badge/skills/londeren/claude-plugins/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 | $0.00208 | $0.08590 |
| Opus 5 | $0.00104 | $0.04295 |
| Sonnet 5 | $0.00042 | $0.01718 |
| Haiku 4.5 | $0.00021 | $0.00859 |
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 10d 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 — 517 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Writer
A skill for writing high-quality LLM prompts (especially for Claude), based on close reading of the Claude system prompts (Opus 4.7, Fable 5, Opus 5) and how attention uses a prompt.
When this skill is active
The user wants to create or improve an instruction for an LLM. It can be a system prompt, a role prompt, an agent instruction, a prompt template, a Claude Project setup, or a specific prompt for a repeatable task. The skill follows a process: understand the task → determine the type → apply the template → audit the draft → deliver the final version.
The process
Step 1: Understand the task
If the user gave a detailed spec with examples, goals, audience, and constraints, do NOT ask clarifying questions, start immediately with inline assumptions. Second-guessing a detailed request hurts.
If the spec is vague ("write a prompt for an assistant"), ask the minimum number of questions needed to determine the prompt type. No more than 2-3 questions at a time.
The minimum that has to be known before starting:
- What the prompt is supposed to do
- Which model or tool the prompt is written for. If it is not stated, assume Claude, mark that assumption inline in the result, and do not spend a question on it. The rules of this skill are calibrated for Claude; for other tools they apply as they are, with no adaptation
- What format and length of output the user expects
- The success criterion, how the user will know the prompt worked
- Who will use it (a single user, a team, end customers)
- Whether there are critical prohibitions (what must NEVER happen)
- Whether an existing prompt is being improved
Output format and length and the success criterion are derived from the task; ask about them only when they do not follow from the spec, and within the limit of 2-3 questions.
Step 2: Determine the prompt type
Read the Routing section below and pick one of five types. The type decides the template and the approach.
Step 3: Apply the template
What ships with it
9 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.
- checklists/input-triage.md 3.7 KB
- checklists/self-check.md 13 KB
- reference/full-rules.md 61 KB
- reference/modal-registers.md 11 KB
- templates/agentic-task.md 9.4 KB
- templates/character-frame.md 10 KB
- templates/extraction-prompt.md 10 KB
- templates/identification-frame.md 8.9 KB
- templates/one-shot-task.md 6.1 KB
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.
- 10d ago First seen · 517 lines · 208 tokens per session scan A 68cb3459f243
prompt-writer is a skill published in the GitHub repository Londeren/claude-plugins (4 stars, last pushed 15d ago), licensed MIT. It adds 208 tokens to every session and 8,590 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…