just-works: Agent for Claude Code

.claude/agents/prompt-writer.md

prompt-writer is an agent for Claude Code from Dynokostya/just-works. It costs 47 tokens per session (464 once invoked), scanned A, original, Apache-2.0.

An agent for writing and editing prompts, which are instructions given to an AI model, along with prompt templates and prompt files. It applies standards for the selected model and checks template syntax.

In plain words
What is it for?
It is for creating or revising prompts in Markdown, text, Jinja templates, or program code, including prompts for Claude, Gemini, and GPT models.
Why use it?
It reduces errors caused by unclear instructions, unsuitable model patterns, or malformed template files.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is Dynokostya/just-works's own configuration. It tells Claude Code how to work on just-works itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything just-works configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Dynokostya/just-works. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Dynokostya/just-works/main/.claude/agents/prompt-writer.md
Clone the repo
git clone --depth 1 https://github.com/Dynokostya/just-works

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/agents/dynokostya/just-works/prompt-writer/github.svg)](https://agentmods.dev/agents/dynokostya/just-works/prompt-writer)
Your own site
<a href="https://agentmods.dev/agents/dynokostya/just-works/prompt-writer"><img src="https://agentmods.dev/badge/agents/dynokostya/just-works/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/agents/dynokostya/just-works/prompt-writer"><img src="https://agentmods.dev/badge/agents/dynokostya/just-works/prompt-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 464 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 $0.00047 $0.00464
Opus 5 $0.00023 $0.00232
Sonnet 5 $0.00009 $0.00093
Haiku 4.5 $0.00005 $0.00046

Measured 4d ago against content hash 41b04dc4e6aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 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.

.claude/agents/prompt-writer.md · 39 lines

What it actually says

Write effective prompts for Claude Fable 5, Claude Opus 5, Gemini 3, and GPT-5.6 following model-specific best practices.

Before Writing

Read existing prompts before editing. Identify the target model from context or file naming conventions, then apply the corresponding skill's patterns.

Target Model Skill
Claude Fable 5 fable-5-prompting
Claude Opus 5 opus-5-prompting
Gemini 3 gemini-3-prompting
GPT-5.6 gpt-5-6-prompting

File Types

  • .j2 / .jinja / .jinja2 -- Jinja templates. Use {# #} comments, {% set %} defaults, conditionals, loops, filters.
  • .txt / .md -- Static prompts. Plain text or markdown with XML tags where appropriate.
  • .py -- Programmatic prompt construction. String formatting or template rendering.

Quality Standards

  • Read existing prompts before editing. Understand what is there before changing it.
  • Keep Jinja syntax clean: defaults at top, comments documenting sections, consistent delimiters.
  • No emojis in prompts unless the user requests them.
  • Examples in prompts should be precise and reflect the exact desired behavior -- the model reproduces what it sees.
  • After editing a Jinja template, validate it parses (e.g. python3 -c "import jinja2, sys; jinja2.Environment().parse(open(sys.argv[1]).read())" file.j2) — don't assume a hook does it.
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. 4d ago First seen · 39 lines · 47 tokens per session scan A 41b04dc4e6aa

Subscribe to this mod's changes

prompt-writer is an agent published in the GitHub repository Dynokostya/just-works (14 stars, last pushed 4d ago), licensed Apache-2.0. It adds 47 tokens to every session and 464 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 2026-09-04.

Related

Other agents, from other repositories

Prompt Builder

Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.

github/awesome-copilot · 24 tokens

prompt-engineer

Expert in prompt engineering for Claude, GPT, Gemini, and Llama models. Specializes in chain-of-thought prompting, structured outputs, few-shot learning, system prompt architecture, and prompt optimization. Use for designing effective prompts, imp...

SteveGJones/ai-first-sdlc-practices · 52 tokens

hyv-veo-prompt-smith

The generative-prompt writer for HearYourVOICE (Phase 4). Looks at the shots still MISSING a source in the shotlist (after CC scouting) and writes copy/paste generation prompts to fill exactly those gaps — no more. Builds each prompt from the measured durations and the veo-prompt guide, applying subject-lock and…

killernay/HearYourVOICE · 124 tokens

prompt-coach

Reviews prompts, scores prompt quality, identifies anti-patterns, and guides iterative refinement. USE FOR: prompt reviews, quality scoring, anti-pattern detection, refinement coaching, and prompt evaluation feedback. DO NOT USE FOR: production prompt deployment, model fine-tuning, or application feature coding.

ivegamsft/basecoat · 61 tokens

ai-ml-engineer

AI/ML engineer for LLM API integration, prompt engineering, ML pipelines, inference optimization, and recommendation systems. Do NOT use for general CRUD work, UI design, or non-AI infrastructure.

ArieGoldkin/claude-forge · 45 tokens

llm-integration-agent

LLM entegrasyon görevlerini üstlenir. Model API çağrıları, prompt tasarımı, tool-use şemaları, token/maliyet yönetimi, LLM çıktı doğrulama.

boranesn/agentic-base · 47 tokens