ralph

ralph is a skill for Claude Code, Codex from IAPro-Community/Orquestrador-Maestro. It costs 14 tokens per session (3,287 once invoked), scanned A, original, Apache-2.0.

A self-referential work loop that continues until the task is complete and includes architect verification.

In plain words
What is it for?
Use it for tasks that need repeated progress checks and architectural verification before completion.
Why use it?
It is intended to reduce the chance of stopping before the work is finished or checked.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex; $skill-name invocation.

Good fit Use it for tasks that need repeated progress checks and architectural verification before completion.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/iapro-community/orquestrador-maestro/ralph
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.

Any agent
npx skills add IAPro-Community/Orquestrador-Maestro --skill ralph
Clone the repo
git clone --depth 1 https://github.com/IAPro-Community/Orquestrador-Maestro

Made for: Claude Code, Codex.

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 ralph

README.md
[![agentmods](https://agentmods.dev/badge/skills/iapro-community/orquestrador-maestro/ralph/github.svg)](https://agentmods.dev/skills/iapro-community/orquestrador-maestro/ralph)
Your own site
<a href="https://agentmods.dev/skills/iapro-community/orquestrador-maestro/ralph"><img src="https://agentmods.dev/badge/skills/iapro-community/orquestrador-maestro/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.

agentmods 80×15 button for ralph

Your own site · 80×15
<a href="https://agentmods.dev/skills/iapro-community/orquestrador-maestro/ralph"><img src="https://agentmods.dev/badge/skills/iapro-community/orquestrador-maestro/ralph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,287 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 151
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00014 $0.03287
Opus 5 $0.00007 $0.01643
Sonnet 5 $0.00003 $0.00657
Haiku 4.5 $0.00001 $0.00329

Measured 11d ago against content hash 470124f3e284, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • ralph — 88% identical, 17 lines differ
codex/skills/ralph/SKILL.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[RALPH + ULTRAWORK - ITERATION {{ITERATION}}/{{MAX}}]

Your previous attempt did not output the completion promise. Continue working on the task.

<Use_When>

  • Task requires guaranteed completion with verification (not just "do your best")
  • User says "ralph", "don't stop", "must complete", "finish this", or "keep going until done"
  • Work may span multiple iterations and needs persistence across retries
  • Task benefits from parallel execution with architect sign-off at the end </Use_When>

<Do_Not_Use_When>

  • User wants a full autonomous pipeline from idea to code -- use autopilot instead
  • User wants to explore or plan before committing -- use plan skill instead
  • User wants a quick one-shot fix -- delegate directly to an executor agent
  • User wants manual control over completion -- use ultrawork directly </Do_Not_Use_When>

<Why_This_Exists> Complex tasks often fail silently: partial implementations get declared "done", tests get skipped, edge cases get forgotten. Ralph prevents this by looping until work is genuinely complete, requiring fresh verification evidence before allowing completion, and using tiered architect review to confirm quality. </Why_This_Exists>

<Execution_Policy>

  • Fire independent agent calls simultaneously -- never wait sequentially for independent work
  • Use run_in_background: true for long operations (installs, builds, test suites)
  • Always pass the model parameter explicitly when delegating to agents
  • Read docs/shared/agent-tiers.md before first delegation to select correct agent tiers
  • Deliver the full implementation: no scope reduction, no partial completion, no deleting tests to make them pass
  • Default to concise, evidence-dense progress and completion reporting unless the user or risk level requires more detail
  • Treat newer user task updates as local overrides for the active workflow branch while preserving earlier non-conflicting constraints
  • If correctness depends on additional inspection, retrieval, execution, or verification, keep using the relevant tools until the execution loop is grounded
  • Continue through clear, low-risk, reversible next steps automatically; ask only when the next step is materially branching, destructive, or preference-dependent </Execution_Policy>

Read the full file on GitHub · 265 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 · 265 lines · 14 tokens per session scan A 470124f3e284

Subscribe to this mod's changes

ralph is a skill published in the GitHub repository IAPro-Community/Orquestrador-Maestro (41 stars, last pushed yesterday), licensed Apache-2.0. It adds 14 tokens to every session and 3,287 once invoked, about $0.0001 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.