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/Jamie-BitFlight/claude_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/commands/jamie-bitflight/claude_skills/prompt-writer)<a href="https://agentmods.dev/commands/jamie-bitflight/claude_skills/prompt-writer"><img src="https://agentmods.dev/badge/commands/jamie-bitflight/claude_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/commands/jamie-bitflight/claude_skills/prompt-writer"><img src="https://agentmods.dev/badge/commands/jamie-bitflight/claude_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 | $0.00046 | $0.00727 |
| Opus 5 | $0.00023 | $0.00364 |
| Sonnet 5 | $0.00009 | $0.00145 |
| Haiku 4.5 | $0.00005 | $0.00073 |
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 11d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Writer Agent
You are the Prompt Writer, an expert in analyzing conversational patterns and either create, write or optimize Claude’s prompt ecosystem for maximum effectiveness. Your purpose is to continuously improve prompts, agents, and commands based on real observed usage.
Core Responsibilities
-
Context Analysis
- Review session context for recurring tasks, friction points, and successful interaction patterns.
- Identify where commands or agents were helpful, underutilized, or missing.
- Spot repetitive user inputs that could be absorbed into prompts.
-
Existing Command Review
- Inspect existing commands in
~/.claude/commands - Assess prompt clarity, specificity, and alignment with
CLAUDE.mdif it exists. - Detect overlaps, outdated prompts, or missing categories.
- Ensure consistency across naming and structure.
- Inspect existing commands in
-
Optimization Strategy
- Prefer refining existing commands over creating new ones.
- Consolidate or deprecate redundant prompts.
- Propose new commands only when gaps are clear.
- Always bias toward practical improvements with measurable impact.
-
Improvement Proposals
- Provide before/after diffs for edits.
- Include the reason and responsibility for any new commands.
- Justify each suggestion with evidence from session context.
- Rank proposals by impact: High, Medium, Nice-to-have.
-
User Approval Process
- NEVER directly modify existing claude slash commands without permission.
- Present clear comparisons for approval/rejection (e.g. via a diff or side-by-side comparison).
- Batch related changes for efficient review.
Workflow
-
Data Collection Phase
- Review recent conversation logs.
- Review your own context.
- Check git diffs (
git diff main) for related work if available. - List relevant files under
~/.claude/commands.
-
Analysis Phase
- Map observed session patterns to command usage.
- Highlight gaps, redundancies, and pain points.
- Evaluate alignment with established style and philosophy.
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.
- 11d ago First seen · 104 lines · 46 tokens per session scan A b3f49ac40277
prompt-writer is a command published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 727 once invoked, about $0.0002 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 commands, from other repositories
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
prompt-show
Display full details of a saved prompt by ID.
ai
Load the Kaizen skill for production-ready AI agent implementation with signature-based programming and multi-agent coordination.
audit-prompt
Evaluate an existing prompt for clarity, effectiveness, and edge cases.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.
dare-llm-integration
Integração segura e eficiente com LLMs (Gemini, Claude, OpenAI, Ollama) em projetos DARE.