ralphy-implement

A coding workflow for implementing an OpenSpec change, where a proposed software change is described in files before it is built. It works through the task checklist, updates code and tests, and reports completion only after verification passes.

In plain words
What is it for?
Use it when a repository has an active change under openspec/changes/ and you need to read its proposal, tasks, and specification updates, then implement and test them.
Why use it?
It gives an agent a repeatable way to turn a written specification into code while keeping implementation and tests aligned.

Command for Claude Code

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/wenqingyu/ralphy-openspec/ralphy-implement
Clone the repo
git clone --depth 1 https://github.com/wenqingyu/ralphy-openspec

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 193 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 $0.00000 $0.00193
Opus 5 $0.00000 $0.00097
Sonnet 5 $0.00000 $0.00039
Haiku 4.5 $0.00000 $0.00019

Measured 2d ago against content hash 2b0d1b8e1ed3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ralphy-implement 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.

.claude/commands/ralphy-implement.md · 31 lines

What it actually says

/ralphy-implement (Implement OpenSpec tasks)

You are implementing an OpenSpec change located under openspec/changes/<change-name>/.

Goal

Complete all tasks in tasks.md and satisfy the acceptance criteria from the spec scenarios.

Ralph loop compatibility

If this command is being executed in an iterative loop:

  • Make progress each iteration
  • Run tests frequently
  • Only declare success when verification passes

Steps

  1. Identify the active change folder under openspec/changes/.
  2. Read the change artifacts:
    • proposal.md
    • tasks.md
    • spec deltas under specs/
  3. Implement tasks in order:
    • Update code
    • Add/update tests
    • Run tests
    • Mark tasks complete ONLY when verified

Completion promise

Only output this exact text when ALL tasks are complete and tests pass:

TASK_COMPLETE

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 · 31 lines · 0 tokens per session scan A 2b0d1b8e1ed3

Subscribe to this mod's changes

ralphy-implement is a command published in the GitHub repository wenqingyu/ralphy-openspec (182 stars, last pushed 7mo ago), licensed BSD-3-Clause. It costs nothing until one of its globs matches a file; then it loads 193 tokens. 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.