A command-driven workflow for finding and managing proposed code-quality improvements. It discovers possible improvements, offers them for human approval, and can turn approved items into development tasks.

Use it to discover, review, approve, delegate, revert, and track improvement tasks, including the status of an unattended improvement loop.

It separates suggestions from actual changes, so improvements are reviewed and approved before work is assigned or automated.

improve — 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/improve

Any agent

npx skills add nodealchemy/powernode-platform --skill improve

Clone the repo

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

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,215 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	$0.00019	$0.01215
Opus 5	$0.00010	$0.00607
Sonnet 5	$0.00004	$0.00243
Haiku 4.5	$0.00002	$0.00121

Measured yesterday against content hash a6d4071211d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

improve 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/improve/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/improve — Discover & Offer Code-Quality Improvements

Surface code-quality improvements, offer them for human approval, and turn approved ones into dev-improve Ralph Loop tasks that /dev-loop (or a platform agent) acts on. Operator-driven (Tier-1). The platform improvement MCP tool is the dual surface — platform agents call the same actions, so this works for Powernode and any other indexed repo.

Usage

/improve discover [repo]           # find + vet + offer improvements
/improve review                    # list pending offers
/improve approve <id>              # approve an offer -> creates a dev-improve task
/improve delegate <id>             # approve + hand the task to a platform agent
/improve revert <id>               # mark a promoted task reverted (ungameable metric signal)
/improve status                    # improvement scoreboard (velocity + revert_rate)
/improve enable-autonomy <agent>   # gated: run dev-improve unattended (off by default)
/improve disable-autonomy          # return dev-improve to operator-driven

discover

Analyze (MCP-first): platform.code_static_analysis, then scripts/pattern-validation.sh; add platform.code_dead_code / platform.code_find_duplicates when asked.
Verify-before-offer (scrutiny gate — mandatory): for EACH candidate, confirm it still reproduces on HEAD. For dead_code/code_duplication, prove zero live callers with platform.code_blast_radius BEFORE proposing a deletion/extraction. Discard anything you cannot reproduce. Record the proof as verifier_evidence.
Classify each vetted finding: code_lint | dead_code | code_duplication | convention_adherence | test_gap.
Core-purity (gate #9): findings under extensions/private/* are auto-tagged to that extension by the tool — never offer them as core/global, and never propose a fix that makes a core file depend on an extension.
Offer each finding: platform.improvement action create_improvement with recommendation_type, title, fingerprint (kind|file|rule), files, fix, verifier_evidence, confidence_score. Idempotent on fingerprint — re-running discover updates, never duplicates.
Report a summary table (kind, title, file, confidence). Do NOT bulk-approve — offers await individual human review (CLAUDE.md bulk-op rule covers auto-discovered code changes).

Read the full file on GitHub · 61 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 · 61 lines · 0 tokens per session scan A a6d4071211d7

Subscribe to this mod's changes

improve is a skill published in the GitHub repository nodealchemy/powernode-platform (2 stars, last pushed 4d ago), licensed MIT. It adds 19 tokens to every session and 1,215 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.

Code review Data and AI LLM Productivity 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