Borrowing it
Nothing to install: this file belongs to junghwaYang/oh-my-codex. 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/junghwaYang/oh-my-codex/main/.codex/skills/ralph/SKILL.mdgit clone --depth 1 https://github.com/junghwaYang/oh-my-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/junghwayang/oh-my-codex/ralph)<a href="https://agentmods.dev/skills/junghwayang/oh-my-codex/ralph"><img src="https://agentmods.dev/badge/skills/junghwayang/oh-my-codex/ralph/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/junghwayang/oh-my-codex/ralph"><img src="https://agentmods.dev/badge/skills/junghwayang/oh-my-codex/ralph.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 | $0.00000 | $0.00375 |
| Opus 5.5 | $0.00000 | $0.00150 |
| Sonnet 5.5 | $0.00000 | $0.00075 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
ralph 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 2mo 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
Ralph Skill
Persistent execution mode that never gives up.
When to Use
- Tasks that MUST complete fully
- Stubborn bugs that resist fixing
- Complex refactoring with many errors
- Any task where partial completion is unacceptable
When NOT to Use
- Exploratory work
- Tasks where "good enough" is acceptable
- Time-sensitive quick fixes
Philosophy
Ralph is named after the "ralph mode" concept: relentless persistence.
"Never give up. Never surrender."
Workflow
1. ATTEMPT
Execute the task
2. VERIFY
Check if truly complete
- All tests pass?
- No errors remaining?
- Meets all criteria?
3. FIX (if needed)
Address failures
4. LOOP
Repeat until verified complete
(No max attempts - ralph doesn't quit)
Verification Checklist
Before declaring complete:
- Code compiles without errors
- All tests pass
- No TypeScript/lint errors
- Functionality verified
- Edge cases handled
Usage
ralph: fix all TypeScript errors in the project
ralph: refactor the auth module to use the new API
ralph: migrate all components to the new design system
Behavior
- No partial completion - Either fully done or still working
- Self-healing - Automatically fixes issues it creates
- Progress tracking - Reports status regularly
- Escalation - Only asks for help when truly stuck
Notes
- Ralph includes ultrawork capabilities (parallel execution)
- Combines persistence with efficiency
- Will loop indefinitely until success
- Use for critical tasks only (token-intensive)
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.
- 2mo ago First seen · 76 lines · 0 tokens per session scan A ee415c70c593
ralph is a skill published in the GitHub repository junghwaYang/oh-my-codex (5 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 375 tokens. 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 2026-08-31.
ralph compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ralphjunghwaYang/oh-my-codex | Skill | 5 | 8mo ago | MIT | A | 0 | Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |