ralphx-swe

ralphx-swe is a skill for Claude Code, Codex from aigentive/RalphX. It costs 66 tokens per session (3,147 once invoked), scanned A, original, Apache-2.0.

A playbook for supervising RalphX, an automated software-development pipeline that moves work from an idea through execution, review, and merging.

In plain words
What is it for?
Use it to start or manage RalphX tasks, respond to items needing attention, recover from failed work, and decide when changes are ready to merge.
Why use it?
It explains when to inspect the pipeline, when to act, and how to handle failures, reviews, and merge conflicts.

Skill for Claude CodeCodex

Part of the ralphx-shared-plugin plugin — 1 skill shipped together

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.

agentmods
npx agentmods add skills/aigentive/ralphx/ralphx-swe
Any agent
npx skills add aigentive/RalphX --skill ralphx-swe
Clone the repo
git clone --depth 1 https://github.com/aigentive/RalphX

Made for: Claude Code, Codex.

Or install ralphx-shared-plugin, the plugin that ships this one along with the rest of its 1 skill.

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 ralphx-swe

README.md
[![agentmods](https://agentmods.dev/badge/skills/aigentive/ralphx/ralphx-swe.svg)](https://agentmods.dev/skills/aigentive/ralphx/ralphx-swe)
Your own site
<a href="https://agentmods.dev/skills/aigentive/ralphx/ralphx-swe"><img src="https://agentmods.dev/badge/skills/aigentive/ralphx/ralphx-swe.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,147 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00066 $0.03147
Opus 5 $0.00033 $0.01573
Sonnet 5 $0.00013 $0.00629
Haiku 4.5 $0.00007 $0.00315

Measured 4d ago against content hash be11c0011b8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ralphx-swe 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 4d 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.

plugins/shared/skills/ralphx-swe/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RalphX SWE Skill — Autonomous Pipeline Playbook

Skill vs Guide: Call v1_get_agent_guide for tool schemas and sequencing rules. This skill teaches judgment: when to act vs observe, how to handle edge cases, what events mean for decision-making. Zero overlap with the guide's API reference content.


1. Bootstrap — Start Here Every Session

Two steps before taking any pipeline action:

Canonical tool naming (read this before any tool call):

Examples in this skill use canonical RalphX method names: v1_*

Host mappings:
- RalphX external MCP methods: v1_*
- Claude/Codex MCP wrappers in some environments: mcp__ralphx__v1_*
- ReefBot integration: ralphx__v1_*

Never invent a namespace from this skill name.
Never call mcp__ralphx-swe__*.

Step 1 — Check attention items (find what needs action right now):

v1_get_attention_items(project_id)
→ Returns escalated_reviews, failed_tasks, merge_conflicts.
→ Address these before doing anything else.

Step 2 — Load tool reference (for argument schemas and preconditions):

v1_get_agent_guide()  → or v1_get_agent_guide(section: "pipeline") for supervision tools

2. Core Principles

Observe before act. Most pipeline states are agent-active (executing, reviewing, merging). Your role in those states is to watch, not interrupt. Only take action in waiting states (review_passed, escalated, qa_failed, merge_conflict, merge_incomplete).

Annotate before you intervene. Before calling any action tool, call v1_create_task_note with your reasoning. This creates an audit trail for humans reviewing your decisions.

Always pair UUIDs with titles. Any task ID you surface in a log, message, or annotation must include the human-readable title. Use v1_get_task_detail or v1_batch_task_status to resolve titles. Format: task-{id} ({Title}).

Webhook chat updates should stay human-first. Machine IDs from RalphX webhook events are stored separately in message/session metadata. In normal user-facing chat updates, prefer human titles and project labels; do not dump raw UUID footers unless the user explicitly asks for them.

Read the full file on GitHub · 222 lines

Files

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.

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. 4d ago First seen · 222 lines · 66 tokens per session scan A be11c0011b8c

Subscribe to this mod's changes

ralphx-swe is a skill published in the GitHub repository aigentive/RalphX (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 66 tokens to every session and 3,147 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.

Related

Other skills, from other repositories

wayfinder

Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

mattpocock/skills · 46 tokens

sap-transport-overview

System-wide inventory of open transport requests — every visible modifiable request, who owns it, how big it is, and supported risk signals such as empty/local requests, explicit locks, and confirmed manifest overlaps. Headers-only and cheap; NO source diffs. Use when asked "what transports are open in the system"…

arc-mcp/arc-1 · 106 tokens

timeline-creator

Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.

mhattingpete/claude-skills-marketplace · 47 tokens

okx-task-watch

监听任务进展 / 帮我盯着任务 / 任务有动静告诉我 / 历史消息 / 未读消息 / 未决策 / 待决策 / 继续监听 / task watch / user watch / monitor task progress / catch me up on tasks / outstanding decisions — OKX A2A user-session task-notification monitor: live long-poll via okx-a2a user watch (also drains backlog of past/missed/unread events on entry) plus…

nirholas/three.ws · 138 tokens

pm-all

Skill "pm-all" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).

wei63w/pm-manager · 8 tokens

bootstrap-prd

Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.

joshukraine/dotfiles · 25 tokens