What is ralph-mission?

A command that starts an autonomous loop for mission-control tasks stored in a tasks.json file. Each task includes requirements that must be met before it is marked complete.

Use it to implement mission tasks, verify their acceptance criteria, update task statuses, create the required commits, and record progress.

It keeps implementation, testing, status updates, commits, and failure tracking tied to individual tasks. The loop can continue through multiple tasks without manual restarting.

ralph-mission — Command for coding agents by sequenzia: A command that starts an autonomous loop for mission-control…

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 commands/sequenzia/claude-plugins/ralph-mission

Clone the repo

git clone --depth 1 https://github.com/sequenzia/claude-plugins

Or install ralph-mission, the plugin that ships this one along with the rest of its 2 commands.

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/commands/sequenzia/claude-plugins/ralph-mission.svg)](https://agentmods.dev/commands/sequenzia/claude-plugins/ralph-mission)

Your own site

<a href="https://agentmods.dev/commands/sequenzia/claude-plugins/ralph-mission"><img src="https://agentmods.dev/badge/commands/sequenzia/claude-plugins/ralph-mission.svg" alt="Measured on agentmods" height="20"></a>

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 384 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.

Model	Per session	Once invoked
Fable 5	$0.00011	$0.00384
Opus 5	$0.00005	$0.00192
Sonnet 5	$0.00002	$0.00077
Haiku 4.5	$0.00001	$0.00038

Measured 3d ago against content hash 1bdb3133e62b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ralph-mission 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 3d 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/ralph-mission/commands/ralph-mission.md · 46 lines

What it actually says

Ralph Mission Command

Execute the setup script to initialize the Ralph Mission loop:

"${CLAUDE_PLUGIN_ROOT}/scripts/setup-ralph-mission.sh" $ARGUMENTS

How It Works

Ralph Mission autonomously iterates through tasks from a mission-control tasks.json file. For each task:

Implement the task completely based on its description and acceptance criteria
Verify all acceptance criteria are met
Run tests if applicable
Update the task status in the tasks.json file:
- Edit the mission file
- Find the current task by ID
- Change "status": "not_started" to "status": "complete"
Commit your changes with: feat: TASK-XXX - <title>

Important Rules

Do NOT mark a task complete unless ALL acceptance criteria are genuinely met
The loop detects completion by checking the task status in the JSON file
Failed attempts (task not completed after your response) increment a counter
After max failed attempts, the task is marked as "blocked" and we move on
Progress and learnings are logged to progress.txt in the mission directory

Stopping the Loop

The loop stops when:

All tasks are complete
All remaining tasks are blocked
Max iterations is reached
You run /ralph-mission:cancel

Trust the process - the loop continues until genuine completion.

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.

3d ago First seen · 46 lines · 11 tokens per session scan A 1bdb3133e62b

Subscribe to this mod's changes

ralph-mission is a command published in the GitHub repository sequenzia/claude-plugins (2 stars, last pushed 7mo ago), licensed MIT. It adds 11 tokens to every session and 384 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 2026-08-31.

Project management

ralph-mission

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Ralph Mission Command

How It Works

Important Rules

Stopping the Loop

What this file has done since we first saw it

Other commands, from other repositories

project-recap

os-meeting

workspace

standup

m-task-planner

triage