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.
npx skills add melodic-software/claude-code-plugins --skill improvegit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote 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.
[](https://agentmods.dev/skills/melodic-software/claude-code-plugins/improve)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/improve"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/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.
<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/improve"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00118 | $0.02186 |
| Opus 5.5 | $0.00047 | $0.00874 |
| Sonnet 5.5 | $0.00024 | $0.00437 |
| Haiku 4.5 | $0.00012 | $0.00219 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments. [deepening|boundaries]. e.g., boundaries
Repository context. Gather first
Collect these with individual Bash calls, one command per call, never combined into a single invocation:
- Current branch,
git branch --show-current - Recent commits,
git log --oneline -20 - Working tree status (empty = clean),
git status --porcelain | head -10
The pipe is the bound and belongs in the command. A read-time cap ("read only the first 10 entries") bounds nothing: the Bash tool returns the command's complete output into context before there is anything to decide about.
Treat a failure (not a repository, git unavailable) as an unknown value and carry on. Keep these as
separate body Bash calls rather than pre-compute lines: the harness runs a skill's whole pre-compute
block as one shell invocation, and a worktree-isolated session refuses a compound command that
contains git. The dated record for that composition claim is the source-control plugin's
worktree/reference/gather-block.md,
"The pre-compute block runs as one shell invocation".
Variables
Arguments: $ARGUMENTS
Purpose
Improvement is distinct from review and planning. Review evaluates a DIFF against criteria (reactive). Planning designs NEW work (forward-looking). This skill scans EXISTING code for friction and proposes candidates for improvement (proactive).
The scan-present-pick process generalizes across improvement lenses. Each lens (action) brings its own analysis method and vocabulary via an actions/<lens>.md playbook plus a research/<lens>/ reference set, loaded only when that lens runs. The first lens, deepening, implements Ousterhout's deep-module concept: finding shallow modules (interface nearly as complex as implementation) and proposing how to deepen them. The aim is testability and AI/agent-navigability (AX): a deep module's small interface lets a reader, human or agent, grasp its purpose without traversing the whole import graph. The boundaries lens checks the module boundaries a repository has recorded against the references its build manifests declare, and hands each rule the user confirms to the enforcement audit as an architecture-test proposal.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- actions/boundaries.md 7.9 KB
- actions/deepening.md 20 KB
- evals/evals.json 14 KB
- research/boundaries/README.md 4.9 KB
- research/deepening/dependencies.md 2.8 KB
- research/deepening/html-report.md 8.3 KB
- research/deepening/interface-design.md 11 KB
- research/deepening/scan-briefing.md 7.7 KB
- research/deepening/vocabulary.md 5.1 KB
- research/enforcement-ladder.md 7.4 KB
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.
- 2d ago Changed · -4 tokens per session 91a6ca1b736d
- 5d ago Changed · +8 lines · +13 tokens per session 5ad177a7752a
- 12d ago Changed d5acd5ed1a15
- 14d ago Changed 8f5f355f497f
- 15d ago Changed 14f61c48eb62
- 17d ago Changed · +2 lines · -57 tokens per session 1f9547c2b44a
- 18d ago Changed c92733867b72
- 19d ago Changed · -60 tokens per session 32cad08e52bf
- 1mo ago Changed · +2 lines 7d15e062eb38
- 1mo ago First seen · 95 lines · 226 tokens per session scan A 73dcb1d6a7a2
improve is a skill published in the GitHub repository melodic-software/claude-code-plugins (26 stars, last pushed today), licensed MIT. It adds 118 tokens to every session and 2,186 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
refactor-decompose-function
For long functions: break into smaller pieces, extract helper functions, reduce nesting, improve testability and readability.
pr-analyzing
Use this skill when the user asks to analyze a specific GitHub pull request, review a PR's architectural impact, assess what changed in a PR and why it matters, or research the code relationships affected by a PR — example triggers like "analyze PR.
catch-expected-errors
For iteration with errors: catch exceptions during exploration, skip invalid cases, continue to next attempt.
find-shortest-path
For pathfinding and search: shortest path, maze solving, game AI, route planning, graph traversal, BFS/DFS, Dijkstra, A problems.
visual-design-system
World-class visual design system standards — OKLCH color science, fluid typography, elevation hierarchy, branded asymmetric corners, and dark mode implementation.
css-coding-standards
CSS coding standards for systemprompt.io — one --sp- token system in OKLCH with color-mix derivation, BEM naming, one component per file, CSS-first behaviour, forbidden constructs, comment rules, and file limits. Canonical source of truth for all CSS. Load before writing or reviewing any stylesheet.