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/darrencroton/ai-agent-coder/code-simplifiernpx skills add darrencroton/ai-agent-coder --skill code-simplifiergit clone --depth 1 https://github.com/darrencroton/ai-agent-coderWhat 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 | $0.00049 | $0.00598 |
| Opus 5 | $0.00024 | $0.00299 |
| Sonnet 5 | $0.00010 | $0.00120 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
code-simplifier 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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Simplifier
Use this skill for a separate improvement pass over code that already works. It is not part of the default scoped-implementation workflow: the user invokes it deliberately, with existing behaviour, tests, or outputs available to compare against. Be ambitious about simplification, but never change what the code does — only how it does it.
Boundaries
- Preserve functionality exactly. Product behaviour, public contracts, data shapes, test meaning, and accepted edge cases are fixed. If a meaningful simplification would require changing any of them, report it as a recommendation instead of making the change.
- Respect frozen contracts. After an implementation-plan or scoped-implementation workflow, treat the implemented behaviour and its accepted edge cases as part of the contract. Simplification is never a back door for scope expansion.
- Use the requested scope. For a holistic pass, inspect enough surrounding code to simplify the design coherently. For a narrow request, refine only the named files or functions.
Standards Come From the Project
Discover conventions rather than importing them: read AGENTS.md, CLAUDE.md, CONTRIBUTING, linter/formatter configuration, and the surrounding code, then match what the project actually does — naming, module layout, error-handling idiom, comment density, import style, test structure. Do not impose conventions from another ecosystem onto this one.
What To Improve
- Reduce unnecessary complexity, nesting, and indirection.
- Eliminate redundant code and abstractions that no longer earn their place.
- Improve names where the current ones obscure intent.
- Consolidate related logic that has drifted apart.
- Remove comments that restate the code; keep the ones that carry constraints the code cannot show.
- Prefer explicit, boring constructs over clever or dense ones — clarity beats brevity, and deeply nested conditional expressions usually read worse than a plain conditional.
What To Avoid
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 · 43 lines · 49 tokens per session scan A 22271a875859
code-simplifier is a skill published in the GitHub repository darrencroton/ai-agent-coder (2 stars, last pushed 6d ago), licensed MIT. It adds 49 tokens to every session and 598 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 2026-08-31.
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…