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 theflixerbox77/ralph-wiggum-codex --skill ralph-prompt-generatorgit clone --depth 1 https://github.com/theflixerbox77/ralph-wiggum-codexWrote 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/theflixerbox77/ralph-wiggum-codex/ralph-prompt-generator)<a href="https://agentmods.dev/skills/theflixerbox77/ralph-wiggum-codex/ralph-prompt-generator"><img src="https://agentmods.dev/badge/skills/theflixerbox77/ralph-wiggum-codex/ralph-prompt-generator/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/theflixerbox77/ralph-wiggum-codex/ralph-prompt-generator"><img src="https://agentmods.dev/badge/skills/theflixerbox77/ralph-wiggum-codex/ralph-prompt-generator.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 | $0.00044 | $0.01696 |
| Opus 5 | $0.00022 | $0.00848 |
| Sonnet 5 | $0.00009 | $0.00339 |
| Haiku 4.5 | $0.00004 | $0.00170 |
Grade A, and why
ralph-prompt-generator 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.
This is a copy
100% identical to ralph-prompt-generator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralph Prompt Generator
Companion skill for $ralph-wiggum-codex.
This skill does not exist to synthesize flags first. Its primary job is to improve the prompt itself through a staged prompt-improvement workflow, then finish with a small Ralph-specific handoff.
Core Rule
Clarify, do not prescribe.
The receiving agent is equally capable. Improve the briefing, preserve the user's boundaries, and avoid doing the downstream agent's job.
When To Use
Use this skill when:
- The source prompt is ambiguous, bloated, or structurally weak.
- The user wants a reusable prompt for
$ralph-wiggum-codex. - The task needs critique and revision, not just runner flag suggestions.
- The user wants saved planning, draft, and final prompt files in the repo.
Do not use this skill when:
- The user already has a production-ready Ralph prompt.
- The user wants
$ralph-wiggum-codexexecuted immediately with no prompt rewrite. - The only missing detail is a minor flag choice that can be handled inline.
Inputs
Primary input:
<user_prompt>
Optional supporting context:
<examples><feedback>
Treat <examples> as demonstrations, not new requirements. Treat <feedback> as revision guidance, not permission to weaken the original constraints.
Repo-Backed Workspace
Use this workspace for all saved outputs:
docs/prompt-improver-spec/artifacts/implementation_plan.mddocs/prompt-improver-spec/artifacts/task.mddocs/prompt-improver-spec/artifacts/walkthrough.mddocs/prompt-improver-spec/final-prompts/<prompt-name>-draft.mddocs/prompt-improver-spec/final-prompts/<prompt-name>.md
Determine <prompt-name> during planning using a descriptive kebab-case filename. Reuse the saved files on resume instead of redoing earlier analysis from scratch.
Delete the draft file after creating the final prompt.
Required Workflow
Follow the staged workflow defined in references/prompt-improver-workflow-codex.md.
Phase A
Planning only. Complete Steps 1-2.
What ships with it
5 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.
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 · 199 lines · 44 tokens per session scan A 69dd68d1ffce
ralph-prompt-generator is a skill published in the GitHub repository theflixerbox77/ralph-wiggum-codex (5 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 1,696 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to ralph-prompt-generator, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
cost-aware-llm-pipeline
A planning guide for choosing language models and managing the amount of conversation context used by an AI coding workflow. It groups tasks by complexity and gives rules for avoiding context overflow during long sessions.
llm-patterns
AI-first application patterns, LLM testing, prompt management.
prompt-engineering
Universal prompt engineering techniques for any LLM. Use when crafting, optimizing, or reviewing prompts for AI models. Triggers on requests like "improve this prompt", "write a system prompt", "optimize my instructions", "help me prompt engineer", "audit this prompt", "review my prompt", or when building agentic…
opik-optimizer
Optimize LLM prompts, tools, and agents in Opik using standardized optimizer workflows (prompt optimization, tool optimization, and parameter tuning), dataset/metric wiring, and result interpretation.
prompt-engineering
Use when one prompt must give the same right answer across reruns, models, and pasted-in hostile input: forcing a fixed schema, picking the few-shot set, ordering the prompt blocks, or the inline cases you run while tuning. NOT the agent loop, tools, or retrieval (that is building-agents), NOT a standing CI eval…
proxy-local-ai-subscriptions
A guide for exposing your local Codex, ChatGPT Codex, or Claude Code subscription through a protected local OpenAI-compatible endpoint, then connecting it to NextClaw as a custom provider.