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/davideagostini/ai-dev-skills/simplify-codenpx skills add davideagostini/ai-dev-skills --skill simplify-codegit clone --depth 1 https://github.com/davideagostini/ai-dev-skillsWhat 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 | $0.00051 | $0.01150 |
| Opus 5 | $0.00026 | $0.00575 |
| Sonnet 5 | $0.00010 | $0.00230 |
| Haiku 4.5 | $0.00005 | $0.00115 |
Grade A, and why
simplify-code 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a pragmatic code reviewer focused on maintainability improvements that do not change behavior.
Your job is to inspect the smallest correct scope for $ARGUMENTS, identify high-signal issues in changed code, and optionally apply only safe, behavior-preserving fixes. Follow the workflow below in order. Read the relevant reference files before reviewing or editing.
Do not churn code just to make it look different. Respect local conventions, instruction files, and module patterns.
MODES
Choose the mode from the user's wording:
review-only: review, audit, check, inspectsafe-fixes: simplify, clean up, refactor, reduce duplicationfix-and-validate: same assafe-fixes, plus run the smallest relevant validation after edits
Default rules:
- If the request says
review,audit, orcheck, usereview-only - If the request says
simplify,clean up, orrefactor, usesafe-fixes - If the user explicitly asks to verify after edits, use
fix-and-validate
WORKFLOW
Step 1 — Determine the review scope
→ Consult scope-and-diff.md
- Prefer explicit user paths over inferred scope
- When using git, choose the smallest correct diff target
- Review staged and unstaged work separately if both exist
- If there is no clear scope, stop and say so briefly
Before reviewing, read the closest applicable local instructions for the touched area, such as AGENTS.md, workflow docs, or module-specific standards.
Step 2 — Decide whether to parallelize
→ Consult parallel-review.md
- For a tiny diff or one very small file, review locally
- For broader changes, use four sub-agents in parallel
- Give each sub-agent the same scope but a different review role
- Ask for concise structured findings only
Use these four review roles:
- Reuse
- Quality
- Efficiency
- Clarity and standards
Use available Codex agent types pragmatically:
explorerfor codebase lookup and reuse discoverydefaultfor deeper review reasoning
What ships with it
6 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.
- 2d ago First seen · 149 lines · 51 tokens per session scan A fc9d382eb06c
simplify-code is a skill published in the GitHub repository davideagostini/ai-dev-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 51 tokens to every session and 1,150 once invoked, about $0.0003 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
add-sample
Create a SamplesApp sample page with correct theming and attributes. Use when adding UI samples for controls.
compose-slot-api-pattern
Use when designing or reviewing a reusable Jetpack Compose component whose visual regions vary by caller, or when primitive content parameters and boolean shape flags are accumulating. Technique-layer skill — complements the codebase-specific compose-expert.
gcloud-usage
This skill should be used when user asks about "GCloud logs", "Cloud Logging queries", "Google Cloud metrics", "GCP observability", "trace analysis", or "debugging production issues on GCP".
spk-team-auth
Handle Spec Kitty team authentication, hosted credentials, account selection, and auth-related recovery.
setup
This skill should be used when user encounters "Azure MCP error", "Azure authentication failed", "az login required", "Azure CLI not found", or needs help configuring Azure MCP integration.
maui-unit-testing
Add and improve automated tests for .NET MAUI apps, focusing on ViewModels, services, platform abstractions, and unit/integration/device test boundaries. USE FOR: xUnit projects, ViewModel tests that avoid MauiProgram.CreateMauiApp, fakes/mocks, MAUI injectable platform interfaces such as…