prompt-writer

prompt-writer is a command for Claude Code from Jamie-BitFlight/claude_skills. It costs 46 tokens per session (727 once invoked), scanned A, original, MIT.

A command that reviews how prompts, agents, and commands were used during a work session and suggests improvements.

In plain words
What is it for?
Use it after substantial work or recurring tasks to review existing prompts, suggest practical changes, and provide before-and-after edits.
Why use it?
It identifies repeated work, confusing instructions, unused tools, and gaps that make future sessions less efficient.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Good fit Use it after substantial work or recurring tasks to review existing prompts, suggest practical changes, and provide before-and-after edits.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jamie-bitflight/claude_skills/prompt-writer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skills

Made for: Claude Code.

Wrote 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.

agentmods badge for prompt-writer

README.md
[![agentmods](https://agentmods.dev/badge/commands/jamie-bitflight/claude_skills/prompt-writer/github.svg)](https://agentmods.dev/commands/jamie-bitflight/claude_skills/prompt-writer)
Your own site
<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.

agentmods 80×15 button for prompt-writer

Your own site · 80×15
<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>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 727 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash b3f49ac40277, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

.claude/commands/prompt-writer.md · 104 lines

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

  1. 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.
  2. Existing Command Review

    • Inspect existing commands in ~/.claude/commands
    • Assess prompt clarity, specificity, and alignment with CLAUDE.md if it exists.
    • Detect overlaps, outdated prompts, or missing categories.
    • Ensure consistency across naming and structure.
  3. 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.
  4. 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.
  5. 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

  1. 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.
  2. Analysis Phase

    • Map observed session patterns to command usage.
    • Highlight gaps, redundancies, and pain points.
    • Evaluate alignment with established style and philosophy.

Read the full file on GitHub · 104 lines

Changes

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.

  1. 11d ago First seen · 104 lines · 46 tokens per session scan A b3f49ac40277

Subscribe to this mod's changes

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.