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.
curl -O https://raw.githubusercontent.com/Dynokostya/just-works/main/.claude/agents/prompt-writer.mdgit clone --depth 1 https://github.com/Dynokostya/just-worksWrote 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/agents/dynokostya/just-works/prompt-writer)<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.
<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>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 | $0.00072 | $0.00497 |
| Opus 5.5 | $0.00029 | $0.00199 |
| Sonnet 5.5 | $0.00014 | $0.00099 |
| Haiku 4.5 | $0.00007 | $0.00050 |
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 9d 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
Write effective prompts for Claude Fable 5.1, Claude Opus 5.5, Gemini 3.x, and GPT-6 following model-specific best practices.
Before Writing
Read existing prompts before editing. Identify the target model from the task, the file's contents, or file naming conventions, then load only the matching skill with the Skill tool and apply its patterns. If the target model is unclear, ask, or infer it from the project's files and config before loading a skill.
| Target Model | Skill |
|---|---|
| Claude Fable 5.1 | fable-5-1-prompting |
| Claude Opus 5.5 | opus-5-5-prompting |
| Gemini 3.x | gemini-3-prompting |
| GPT-6 (Astra, Sol, Luna) | gpt-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.
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.
- 9d ago Changed · +25 tokens per session 664ef6b45dec
- 17d ago Changed · -5 lines a7647b38bca4
- 1mo ago Changed 0fcf196d0791
- 1mo ago Changed · -1 lines 192744cba74d
- 2mo ago First seen · 39 lines · 47 tokens per session scan A 41b04dc4e6aa
prompt-writer is an agent published in the GitHub repository Dynokostya/just-works (14 stars, last pushed 10d ago), licensed Apache-2.0. It adds 72 tokens to every session and 497 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 2026-09-04.
prompt-writer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| prompt-writerDynokostya/just-works | Agent | 14 | 10d ago | Apache-2.0 | A | 72 | Claude Code |
| Prompt Buildergithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 24 | Claude Code |
| tokentonone-ai/tonone | Agent | 77 | 23d ago | MIT | A | 21 | Claude Code |
| security-ai-codejoaoguirunas/team-os | Agent | 6 | 4d ago | MIT | A | 94 | Claude Code |
| prompt-engineerSteveGJones/ai-first-sdlc-practices | Agent | 42 | 1mo ago | MIT | B | 52 | Claude Code |
| prompt-coachivegamsft/basecoat | Agent | 4 | 7d ago | MIT | A | 61 | Claude Code |
| hyv-veo-prompt-smithkillernay/HearYourVOICE | Agent | 141 | 3mo ago | MIT | B | 124 | Claude Code |