improve

improve is a skill for Claude Code, Codex from jamesgray-ai/handsonai-plugins. It costs 103 tokens per session (1,746 once invoked), scanned A, original, MIT.

A review process for a running AI workflow that checks its quality and compares its current results with its original baseline.

In plain words
What is it for?
Use it to load workflow records and test results, inspect run history, find improvement opportunities, and recommend the next change.
Why use it?
It helps identify declining performance or new requirements and decide whether the workflow needs tuning, redesign, or a different orchestration approach.

Skill for Claude CodeCodex

Part of the handsonai plugin — 13 skills, 1 agent shipped together

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/jamesgray-ai/handsonai-plugins/improve
Any agent
npx skills add jamesgray-ai/handsonai-plugins --skill improve
Clone the repo
git clone --depth 1 https://github.com/jamesgray-ai/handsonai-plugins

Made for: Claude Code, Codex.

Or install handsonai, the plugin that ships this one along with the rest of its 13 skills, 1 agent.

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.

agentmods badge for improve

README.md
[![agentmods](https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/improve.svg)](https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/improve)
Your own site
<a href="https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/improve"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/improve.svg" alt="Measured on agentmods" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,746 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 $0.00103 $0.01746
Opus 5 $0.00051 $0.00873
Sonnet 5 $0.00021 $0.00349
Haiku 4.5 $0.00010 $0.00175

Measured 4d ago against content hash 0615bcf7292c, 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 4d 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.

plugins/handsonai/skills/improve/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Improve Workflow

Evaluate and evolve running AI workflows. Review how a deployed workflow is performing against its original baseline, identify degradation or growth signals, and recommend whether to tune, redesign, or evolve the orchestration mechanism.

Workflow

1. Load workflow context

Registry entry: the workflow's registry entry is its Workflow concept node in the workspace's registry/ bundle — see indexing-registry/references/registry-bundle.md (in this plugin) for resolution, write rules, and your fields. If the workspace has no registry/SCHEMA.md, offer the scaffolding-registry skill first (it also migrates legacy workflow.yaml workspaces); do not write registry entries until the bundle exists.

Read the workflow's Workflow node (registry/workflows/<slug>.md) and load the artifacts it links: the Design Spec, Run Guide, original Test Results (the baseline), and the run log (runs.md) if one exists. Resume orientation: if the user arrived via "continue my workflow" or with no stated workflow, check registry/workflows/ for existing Workflow nodes (if several, list them) and orient from which artifacts each node's # Artifacts section already links before proceeding. If no Workflow node exists yet but legacy flat files (outputs/[name]-*.md) do, use those paths. If this environment has no persistent workspace and the files aren't present, ask the user to reconnect your registry repo via the GitHub connector, or re-upload the bundle folder, instead of failing.

Confirm the artifacts belong to the same workflow — check that the workflow field in the Test Results frontmatter matches the Workflow node before treating its scores as this workflow's baseline. Parse the baseline scores from the Test Results frontmatter (scores and averages) — that's the regression reference.

Check the review schedule. If the Workflow node has a stale_after date, compare it to today: if overdue, note it plainly ("This review was due [date] — good timing") and, at the end of this run, agree a fresh stale_after date. If the user arrived well before the date, ask what prompted the early check — that signal (quality slipped, requirements changed) often points straight at the diagnosis.

Read the full file on GitHub · 115 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. 4d ago First seen · 115 lines · 103 tokens per session scan A 0615bcf7292c

Subscribe to this mod's changes

improve is a skill published in the GitHub repository jamesgray-ai/handsonai-plugins (8 stars, last pushed 23d ago), licensed MIT. It adds 103 tokens to every session and 1,746 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens