ralph-conductor

ralph-conductor is an agent for Claude Code from TheBeardedBearSAS/claude-craft. It costs 24 tokens per session (1,057 once invoked), scanned A, original, MIT.

An agent for orchestrating Ralph Wiggum v2.0 sessions, which repeatedly run a task until its Definition of Done (DoD)—the agreed completion criteria—is met.

In plain words
What is it for?
Use it to manage long-running agent tasks, check completion criteria after each iteration, apply task-specific stop thresholds, and monitor session health.
Why use it?
It helps track iterative work, validate completion, recover sessions, detect error loops, and monitor stalled or overly large contexts.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions Claude Code.

Part of the claude-craft plugin — 56 skills, 94 commands, 47 agents, 5 hooks shipped together

Good fit Use it to manage long-running agent tasks, check completion criteria after each iteration, apply task-specific stop thresholds, and monitor session health.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/thebeardedbearsas/claude-craft/ralph-conductor
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.

Clone the repo
git clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craft

Made for: Claude Code.

Or install claude-craft, the plugin that ships this one along with the rest of its 56 skills, 94 commands, 47 agents, 5 hooks.

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-conductor

README.md
[![agentmods](https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/ralph-conductor.svg)](https://agentmods.dev/agents/thebeardedbearsas/claude-craft/ralph-conductor)
Your own site
<a href="https://agentmods.dev/agents/thebeardedbearsas/claude-craft/ralph-conductor"><img src="https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/ralph-conductor.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,057 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. ✓ AI security review Sonnet 5 · 6 Sept 2026 📄 Read the review
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 $0.00024 $0.01057
Opus 5 $0.00012 $0.00528
Sonnet 5 $0.00005 $0.00211
Haiku 4.5 $0.00002 $0.00106

Measured 9d ago against content hash 6663eb95c2e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ralph-conductor 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.

.claude/agents/ralph-conductor.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Ralph Conductor v2.0

Vous etes un agent specialise pour orchestrer les sessions de boucle continue Ralph Wiggum v2.0. Votre role est de guider les taches a travers l'execution iterative de Claude jusqu'a ce que les criteres Definition of Done (DoD) soient satisfaits.

Responsabilites principales

1. Gestion de session

  • Initialiser les sessions Ralph avec configuration appropriee
  • Suivre la progression et les metriques
  • Gerer l'etat de session et la recuperation
  • Surveiller le dashboard temps reel
  • Exporter les metriques (JSON/Prometheus)

2. Validation Definition of Done

  • Evaluer les criteres DoD a chaque iteration
  • Utiliser les templates DoD specifiques a la technologie
  • Fournir des retours sur les criteres reussis/echoues

3. Circuit Breaker Adaptatif (v2.0)

  • Detecter le profil de tache depuis les mots-cles
  • Appliquer les seuils specifiques au profil
  • Apprendre des resultats historiques

4. Monitoring de Sante (v2.0)

  • Detecter les patterns de blocage
  • Identifier les spirales d'erreurs
  • Surveiller le gonflement du contexte

5. Integration Hooks (v2.0)

  • Gerer les hooks Claude Code 2.1.23+
  • Injecter le contexte Ralph au SessionStart
  • Injecter le statut DoD au PreToolUse
  • Bloquer Stop si DoD non satisfait

Profils Adaptatifs v2.0

Profil Mots-cles Comportement
quick_fix fix, bug, typo Seuils agressifs, arret rapide
small_feature add, implement Approche equilibree
medium_feature feature, create Seuils standards
large_feature refactor, migrate Seuils tolerants
exploration explore, investigate Tres tolerant, iterations elevees

Templates DoD par technologie

Technologie Framework Test Outil Lint
Symfony PHPUnit PHPStan
Flutter flutter_test flutter_lints
React Jest/Vitest ESLint
Python pytest ruff
.NET xUnit Analyzers
Go go test golangci-lint
Rust cargo test clippy

Read the full file on GitHub · 116 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. 9d ago First seen · 116 lines · 24 tokens per session scan F 6663eb95c2e0

Subscribe to this mod's changes

ralph-conductor is an agent published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 5d ago), licensed MIT. It adds 24 tokens to every session and 1,057 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.

Related

Other agents, from other repositories

mobile-release-manager

App store submissions, mobile CI/CD, ASO, code signing, and beta distribution specialist. Use when preparing app releases, setting up mobile CI/CD, or managing app store presence. Trigger phrases: app store, Play Store, TestFlight, release, code signing, provisioning profile, Fastlane, ASO, beta, OTA update, version…

travisjneuman/.claude · 77 tokens

ux-researcher

UX research, usability testing, user interviews, wireframing, and information architecture specialist. Use when planning user research, designing interfaces, conducting heuristic evaluations, or creating wireframes. Trigger phrases: UX research, user research, usability, wireframe, user interview, persona, journey…

travisjneuman/.claude · 69 tokens

microservices-architect

Expert microservices architect for distributed system design, service decomposition, and resilience patterns.

travisjneuman/.claude · 20 tokens

dnp-fable-advisor

🧠 Senior .NET advisor to the implementation agents — advises, never implements. Three modes via brief: ADVISE (contract-altitude guidance before hard cross-layer work), UNBLOCK (an implementer is looping or plateaued), ADJUDICATE (verify a suspect agent claim against the code). Consult at decision points, not before…

zdanovichnick/dotnet-pilot · 80 tokens

gsd-ui-checker

Validates UI-SPEC.md design contracts against 6 quality dimensions. Produces BLOCK/FLAG/PASS verdicts. Spawned by /gsd:ui-phase orchestrator.

travisjneuman/.claude · 42 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens