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 agentmods add skills/alleneubank/claude-code/improvenpx skills add alleneubank/claude-code --skill improvegit clone --depth 1 https://github.com/alleneubank/claude-codeWhat 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 | $0.00035 | $0.01140 |
| Opus 5 | $0.00017 | $0.00570 |
| Sonnet 5 | $0.00007 | $0.00228 |
| Haiku 4.5 | $0.00003 | $0.00114 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- improve — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve
Structured improvement pass grounded in what was observed during this session.
Principles (Always Active)
- Every suggestion must cite a specific observation — file path, error seen, pattern noticed, or behavior verified. "I saw X" beats "common practice suggests Y."
- Distinguish grounded suggestions (observed evidence) from speculative ones (general knowledge). Mark speculative suggestions explicitly.
- Prioritize by impact to the user, not by ease of description.
- Do not suggest improvements that would change public API contracts, auth boundaries, or data schemas without flagging as high-risk.
- Simplicity is a feature. Do not suggest adding complexity unless it prevents a concrete problem observed in this session.
When to Use
- User asks "knowing what you know now, what are some improvements?" or similar
- Before claiming done in a ralph loop (self-check)
- Before generating a handoff
- After completing a significant chunk of work
- When reviewing code that was just written or modified
When Not to Use
- At the start of a session before meaningful work has been done
- When the user explicitly asks to skip review and ship
- For architectural redesigns (use spec/plan flow instead)
Dimensions
Analyze across these dimensions. Skip any dimension with nothing grounded to say.
Correctness
Error handling gaps, unhandled edge cases, type safety issues, race conditions, missing validation at system boundaries.
Simplicity
Unnecessary indirection, dead code, naming that obscures intent, over-engineered abstractions, complexity that doesn't earn its keep. Reference the simplify skill for implementation.
Security
Auth boundary gaps, input validation holes, secret handling issues, OWASP concerns observed in touched code.
Test Coverage
Untested code paths observed during the session, missing test layers (unit/integration/e2e), fixture realism gaps, assertions that don't verify meaningful behavior.
Performance
Bottlenecks observed during the session (slow queries, N+1 patterns, unnecessary recomputation). Only flag what was actually observed, not hypothetical.
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 First seen · 120 lines · 35 tokens per session scan A 51cb0871a0c8
improve is a skill published in the GitHub repository alleneubank/claude-code (52 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,140 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…