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.

How nodealchemy/powernode-platform configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to nodealchemy/powernode-platform. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/nodealchemy/powernode-platform/develop/.claude/skills/improve/SKILL.md

Clone the repo

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

Made for: Claude Code.

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/skills/nodealchemy/powernode-platform/improve/github.svg)](https://agentmods.dev/skills/nodealchemy/powernode-platform/improve)

Your own site

<a href="https://agentmods.dev/skills/nodealchemy/powernode-platform/improve"><img src="https://agentmods.dev/badge/skills/nodealchemy/powernode-platform/improve/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nodealchemy/powernode-platform/improve"><img src="https://agentmods.dev/badge/skills/nodealchemy/powernode-platform/improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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

When invoked 1,197 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00000	$0.01197
Opus 5.5	$0.00000	$0.00479
Sonnet 5.5	$0.00000	$0.00239
Haiku 4.5	$0.00000	$0.00120

Measured 1mo ago against content hash 6be6a2abe5a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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/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.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.

1mo ago Changed 6be6a2abe5a0
2mo ago 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 (4 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,197 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.

Code review LLM Planning agent-orchestration ai ai-agents control-plane knowledge-graph

github_read

Read access: repos, issues, PRs, files, branches, workflows, runs.

ParendumOU/Nexora · 0 tokens

accurate-code

Use when implementing or modifying code with Kontext Brain so each behavior-bearing logic unit is grounded in current provenance-backed decisions, domain terms, invariants, and Evidence.

hj1105/kontext-brain-ts · 36 tokens

rigorous-review

Review code, docs, or plans for correctness risks, missing evidence, unclear tradeoffs, and untested assumptions.

cherninlab/ennodia · 27 tokens

dev-review

Code-focused plan-bounce-execute workflow between Claude Code (Opus) and Codex CLI. Use when the user wants repo files changed, a bug fixed, a feature implemented, or a code plan verified before execution. One AI composes a plan, it bounces between agents with [CONTESTED]/[CLARIFY] markers until refined, then the…

alanshurafa/co-evolution · 176 tokens

gaia-curation-review

Review a Gaia curation PR or branch as a read-only merge gate. Use for canonical registry promotion, schema, evidence, prerequisite, nomenclature, installability, and generated-artifact checks. Route intake batches to /gaia-draft-curate and unrelated PRs to /review.

gaia-research/gaia-skill-tree · 64 tokens

review

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use…

gaia-research/gaia-skill-tree · 95 tokens

powernode-platform: Skill for Claude Code