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/dmoskov/sharedskills/code-cleanupnpx skills add dmoskov/sharedskills --skill code-cleanupgit clone --depth 1 https://github.com/dmoskov/sharedskillsWhat 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 | $0.00025 | $0.00572 |
| Opus 5 | $0.00013 | $0.00286 |
| Sonnet 5 | $0.00005 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
code-cleanup 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.
What it actually says
Code Cleanup Skill
A set of focused cleanup skills. Each targets exactly one concern and produces a diagnostic summary before making any changes. Based on the "cleanup waves" pattern.
Sub-Skills
| Sub-Skill | What It Does |
|---|---|
dead-code |
Remove unused imports, unreachable code, unused functions |
error-handling |
Find bare except/catch, missing error handling, silent failures |
type-annotations |
Add missing type annotations (Python: mypy, TS: strict mode) |
extract-functions |
Find functions >50 lines and extract logical units |
Usage
Run all sub-skills sequentially:
/code-cleanup
Or run a specific sub-skill by mentioning it:
"clean up dead code"
"audit error handling"
"add type annotations"
"extract long functions"
Workflow
Each sub-skill follows the same pattern:
- Scan — Search the codebase for the target pattern
- Diagnose — Produce a summary table of findings with file paths and line numbers
- Confirm — Present findings to the user before making changes
- Fix — Apply targeted fixes, one file at a time
- Verify — Run lint/tests to confirm nothing broke
Prompts
Each sub-skill has its own prompt in prompts/:
prompts/dead-code.md— Unused imports, unreachable code, dead functionsprompts/error-handling.md— Bare except, silent failures, missing handlersprompts/type-annotations.md— Missing types for Python (mypy) and TypeScript (strict)prompts/extract-functions.md— Long functions, logical extraction points
Running All Sub-Skills
When triggered with the generic "code cleanup" command, run each sub-skill in order:
- Dead code (safest — only removes, never adds)
- Error handling (adds safety, rarely breaks things)
- Type annotations (additive, improves tooling)
- Extract functions (structural change — do last)
Commit after each sub-skill completes so changes are atomic and reviewable.
What ships with it
5 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.
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 · 77 lines · 25 tokens per session scan A f8c575699776
code-cleanup is a skill published in the GitHub repository dmoskov/sharedskills (2 stars, last pushed 11d ago), licensed MIT. It adds 25 tokens to every session and 572 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.
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…