ralph_plan

A command that finds the highest-priority small Linear ticket marked “ready for spec” and starts an implementation plan for it. Linear is a tool for tracking software work.

In plain words
What is it for?
Use it to select a small ticket, save its details, review related discussion, update its status to “plan in progress,” and prepare or locate its implementation plan.
Why use it?
It removes the manual work of finding the next suitable ticket, reading its history and comments, and checking whether a plan already exists.

Command

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/jeffh/claude-plugins/ralph_plan
Clone the repo
git clone --depth 1 https://github.com/jeffh/claude-plugins
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 601 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 $0.00011 $0.00601
Opus 5 $0.00005 $0.00300
Sonnet 5 $0.00002 $0.00120
Haiku 4.5 $0.00001 $0.00060

Measured 2d ago against content hash edffa4137aa5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ralph_plan 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 2d 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.

humanlayer/commands/ralph_plan.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PART I - IF A TICKET IS MENTIONED

0c. use linear cli to fetch the selected item into thoughts with the ticket number - ./thoughts/shared/tickets/ENG-xxxx.md 0d. read the ticket and all comments to learn about past implementations and research, and any questions or concerns about them

PART I - IF NO TICKET IS MENTIONED

  1. read .claude/commands/linear.md 0a. fetch the top 10 priority items from linear in status "ready for spec" using the MCP tools, noting all items in the links section 0b. select the highest priority SMALL or XS issue from the list (if no SMALL or XS issues exist, EXIT IMMEDIATELY and inform the user) 0c. use linear cli to fetch the selected item into thoughts with the ticket number - ./thoughts/shared/tickets/ENG-xxxx.md 0d. read the ticket and all comments to learn about past implementations and research, and any questions or concerns about them

PART II - NEXT STEPS

think deeply

  1. move the item to "plan in progress" using the MCP tools 1a. read ./claude/commands/create_plan.md 1b. determine if the item has a linked implementation plan document based on the links section 1d. if the plan exists, you're done, respond with a link to the ticket 1e. if the research is insufficient or has unaswered questions, create a new plan document following the instructions in ./claude/commands/create_plan.md

think deeply

  1. when the plan is complete, attach the doc to the ticket using the MCP tools and create a terse comment with a link to it (re-read .claude/commands/linear.md if needed) 2a. move the item to "plan in review" using the MCP tools

think deeply, use TodoWrite to track your tasks. When fetching from linear, get the top 10 items by priority but only work on ONE item - specifically the highest priority SMALL or XS sized issue.

PART III - When you're done

Print a message for the user (replace placeholders with actual values):

✅ Completed implementation plan for ENG-XXXX: [ticket title]

Approach: [selected approach description]

The plan has been:

Created at thoughts/shared/plans/YYYY-MM-DD-ENG-XXXX-description.md
Saved to thoughts directory
Attached to the Linear ticket
Ticket moved to "plan in review" status

Implementation phases:
- Phase 1: [phase 1 description]
- Phase 2: [phase 2 description]
- Phase 3: [phase 3 description if applicable]

View the ticket: https://linear.app/humanlayer/issue/ENG-XXXX/[ticket-slug]

Read the full file on GitHub · 60 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. 2d ago First seen · 60 lines · 11 tokens per session scan A edffa4137aa5

Subscribe to this mod's changes

ralph_plan is a command published in the GitHub repository jeffh/claude-plugins (12 stars, last pushed 18d ago), licensed Apache-2.0. It adds 11 tokens to every session and 601 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.