A shortcut for consensus planning: several planning roles repeatedly review a proposed implementation plan until they agree. It can also ask you to review decisions and add extra checks for high-risk work.

Use it to prepare plans for ambiguous or risky coding tasks, especially changes involving security, migrations, destructive actions, production incidents, or compliance.

It helps expose missing requirements, design disagreements, and risks before coding begins.

ralplan — Skill for Claude Code and Codex by mrzhangguoguo

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 mrzhangguoguo/oh-my-workbuddy --skill ralplan

Clone the repo

git clone --depth 1 https://github.com/mrzhangguoguo/oh-my-workbuddy

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mrzhangguoguo/oh-my-workbuddy/ralplan/github.svg)](https://agentmods.dev/skills/mrzhangguoguo/oh-my-workbuddy/ralplan)

Your own site

<a href="https://agentmods.dev/skills/mrzhangguoguo/oh-my-workbuddy/ralplan"><img src="https://agentmods.dev/badge/skills/mrzhangguoguo/oh-my-workbuddy/ralplan/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mrzhangguoguo/oh-my-workbuddy/ralplan"><img src="https://agentmods.dev/badge/skills/mrzhangguoguo/oh-my-workbuddy/ralplan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,460 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00064	$0.01460
Opus 5	$0.00032	$0.00730
Sonnet 5	$0.00013	$0.00292
Haiku 4.5	$0.00006	$0.00146

Measured 11d ago against content hash 56faaa23b339, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ralplan 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.

skills/ralplan/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ported from oh-my-codex ralplan. OMX runtime conventions ($macro invocation, omx CLI, .omx/ state directory) are replaced with WorkBuddy idioms (Skill tool, Agent tool, task list, .workbuddy/memory).

Ralplan (Consensus Planning Alias)

Ralplan is a shorthand alias for plan --consensus. It triggers iterative planning with Planner, Architect, and Critic roles until consensus is reached, with RALPLAN-DR structured deliberation (short mode by default, deliberate mode for high-risk work). An advisory ontology reviewer (Scholastic-style) may inform the plan for ontology-heavy evidence but is not part of the durable consensus gate.

Usage

ralplan "task description"
ralplan --interactive "task description"
ralplan --deliberate "task description"

Flags

--interactive: Enables user prompts at key decision points (draft review and final approval). Without it the workflow runs fully automated and outputs the final plan.
--deliberate: Forces deliberate mode for high-risk work (adds pre-mortem + expanded test planning). Can also auto-enable when the request signals high risk (auth/security, migrations, destructive changes, production incidents, compliance/PII, public API breakage).

Behavior

This skill simply invokes the plan skill in consensus mode:

skill: plan   (with consensus; add --interactive / --deliberate as requested)

The consensus workflow (full detail in the plan skill):

Planner creates an adaptive plan (right-sized, not exactly five steps) and a compact RALPLAN-DR summary (Principles 3-5, Decision Drivers top 3, Viable Options ≥2 with bounded pros/cons; invalidation rationale if only one remains; deliberate mode adds pre-mortem + expanded test plan).
User feedback (--interactive only): present the draft + Principles/Drivers/Options via AskUserQuestion (Proceed to review / Request changes / Skip review). Otherwise auto-proceed.
Architect reviews for soundness via a separate Agent call (strongest steelman antithesis, a real tradeoff tension, synthesis); await completion before step 4.
Critic evaluates via a separate Agent call, only after step 3 (principle-option consistency, fair alternatives, risk clarity, testable criteria, verification steps).
Re-review loop (max 5): any non-APPROVE verdict re-runs Planner→Architect→Critic until APPROVE or 5 iterations; then present the best version.
On Critic approval (--interactive only): present approval options via AskUserQuestion (ultragoal / team / explicit ralph fallback / specialized goal-mode follow-up / Request changes / Reject). Final plan includes ADR, available-agent-types roster, staffing guidance, team launch hints, team verification path, Goal-Mode Follow-up Suggestions. Otherwise output the final plan and stop.
(--interactive only) On approval: invoke ultragoal (default), team, the selected specialized goal-mode follow-up (autoresearch-goal / performance-goal), or ralph only when explicitly selected — never implement directly.

Read the full file on GitHub · 75 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.

11d ago First seen · 75 lines · 64 tokens per session scan A 56faaa23b339

Subscribe to this mod's changes

ralplan is a skill published in the GitHub repository mrzhangguoguo/oh-my-workbuddy (2 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 1,460 once invoked, about $0.0003 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 2026-08-31.

Planning agent-skills oh-my-codex skills workbuddy

claude-md-improver

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…

anthropics/claude-plugins-official · 82 tokens

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

gke-reliability

Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).

google/skills · 73 tokens

gke-workload-security

Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…

google/skills · 181 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens