A one-task work loop that takes the next item from a project queue, changes the code, verifies the result, commits it, and reports what happened. A queue is an ordered list of pending work.

Use it to process one improvement task at a time from a Ralph Loop queue, including resuming tasks that were already claimed or stopping when the queue is empty.

It turns a queued task into a repeatable development cycle with checks and a saved result.

dev-loop — Skill by nodealchemy

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/nodealchemy/powernode-platform/dev-loop

Any agent

npx skills add nodealchemy/powernode-platform --skill dev-loop

Clone the repo

git clone --depth 1 https://github.com/nodealchemy/powernode-platform

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,428 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	$0.00000	$0.01428
Opus 5	$0.00000	$0.00714
Sonnet 5	$0.00000	$0.00286
Haiku 4.5	$0.00000	$0.00143

Measured yesterday against content hash 486624284170, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-loop 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 yesterday.

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/skills/dev-loop/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dev-loop — Execute One Dev-Loop Iteration

Pull the next task from a platform Ralph Loop queue (via the dev_loop MCP bridge) and drive it to a verified, committed, reported outcome. One task per invocation — this is a Ralph-pattern loop body designed to be driven repeatedly by /loop /dev-loop.

Usage

/dev-loop                      # default loop: dev-improve
/dev-loop <loop-name-or-id>    # any other claude_code Ralph Loop

Iteration Workflow

1. Pull

Call platform.dev_next_task(loop_id: "<loop>").

halted: true → report the reason (emergency_halt / schedule_paused / loop state / max_iterations) and STOP. If running under /loop, end the recurring loop.
queue_empty: true → report queue snapshot and STOP (end /loop if active).
Task returned → read loop.loop_spec_path (workload PROMPT.md) and obey loop.guardrails for the rest of the iteration. reclaimed: true means you (or a crashed prior session) already claimed it — resume, don't restart blindly: check the working tree and loop branch for partial work first.

2. Re-verify the claim

Findings rot. Before changing anything, confirm the task's claim against current code:

MCP-first: platform.query_learnings (the area), platform.code_file_skeleton / platform.code_blast_radius on task.metadata.files. Read only the relevant file sections.
task.metadata.repro documents a reproduction — read it, but do not run mutating repro commands against the live DB. Reproduce inside a spec (test DB) instead.
If the claim no longer holds (already fixed elsewhere), report outcome: passed with a summary explaining it is already resolved and check_results showing your verification. Do not invent work.

3. Branch

Identify the affected repo(s) from task.metadata.files (extensions/system/... vs server/... etc.). In each affected repo:

git rev-parse --show-toplevel to confirm where you are (CLAUDE.md submodule safety).
Check out the loop branch (loop.branch, e.g. dev-loop/dev-improve); create it from the current HEAD if it doesn't exist. Leave it checked out for subsequent iterations in the same run.

Read the full file on GitHub · 102 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.

yesterday First seen · 102 lines · 0 tokens per session scan A 486624284170

Subscribe to this mod's changes

dev-loop is a skill published in the GitHub repository nodealchemy/powernode-platform (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,428 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 2026-08-31.

Data and AI LLM Planning agent-orchestration ai ai-agents control-plane knowledge-graph

good-first-issue-batch

File a batch of contributor-ready GitHub issues from the seeds backlog, re-verifying every candidate against HEAD first so no dead issue reaches a contributor. Activate for prompts like "file some good first issues", "open a batch of GFIs", "publish backlog issues to GitHub", "find contributor-ready work", or after an…

jayminwest/warren · 80 tokens

seeds-issue-audit

Audit and triage open Seeds (sd) issues — find which can be closed, auto-close high-confidence completed ones, and report borderline cases. Activate for prompts like "audit open issues", "which seeds issues can be closed", "clean up the issue tracker", "triage the seeds backlog".

jayminwest/warren · 67 tokens

os-eco-dep-sync

Bump warren onto the latest published @os-eco/ versions across package.json + bun.lock and the Dockerfile CLI pins, then run the gates and open a PR. Use when checking if warren is on the newest burrow/plot/canopy/seeds/mulch/sapling.

jayminwest/warren · 69 tokens

release

Prepare, cut, and verify a warren release — tracker audits, version bump, CHANGELOG curation, ROADMAP update, push, then watch the pipeline through to published artifacts.

jayminwest/warren · 39 tokens

warren-dogfood-pipeline

Full prioritize → dispatch → shepherd → track pipeline against the live warren instance. Audits the seeds backlog around a focus theme, dispatches the surviving issues to warren agents one at a time, babysits the resulting PRs to merge (update-branch, conflict-repair runs, auto-merge), and closes the loop in the…

jayminwest/warren · 116 tokens

canvas

Display HTML content on connected Mayros nodes (Mac app, iOS, Android).

ApiliumCode/mayros · 0 tokens