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/nexus-substrate/nexus-agents/code-simplificationnpx skills add nexus-substrate/nexus-agents --skill code-simplificationgit clone --depth 1 https://github.com/nexus-substrate/nexus-agentsWhat 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 | $0.00062 | $0.01289 |
| Opus 5 | $0.00031 | $0.00645 |
| Sonnet 5 | $0.00012 | $0.00258 |
| Haiku 4.5 | $0.00006 | $0.00129 |
Grade A, and why
code-simplification 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Simplification Skill
When to trigger
Apply when:
- Features work and tests pass — simplification is a separate phase
- Code review flagged readability (deep nesting, long functions, unclear names)
- You're touching the area for an unrelated reason and the existing code obstructs understanding
- A new contributor (human or agent) was confused by the same code twice
Skip when:
- The code is already clean or follows the canonical pattern
- You don't fully understand what the code does (Chesterton's Fence — see below)
- Performance is critical and the "simplification" would change hot-path semantics
- Tests don't exist yet — write them first (
test-driven-developmentskill)
The five principles
- Preserve behavior exactly. Ask: "Does this produce the same output for every input — including the inputs the original author was paranoid about?"
- Follow project conventions. Match the existing codebase, not your external preferences. The
.rules/directory and CLAUDE.md describe what's canonical here. - Prefer clarity over cleverness. Explicit beats compact when the reader has to "decompile" the line in their head.
- Maintain balance. Don't over-inline (one giant function), don't over-extract (10 micro-helpers each used once).
- Scope to what changed. Drive-by refactors in unrelated files inflate diffs and hide regressions. Open a follow-up PR.
Chesterton's Fence
"Don't remove a fence in the middle of a field until you understand why it was put there."
Before deleting code, comment, or guard clause:
- Search for the issue or commit that added it (
git log -S "term" --all,git blame). - Understand the original intent. A weird-looking check often guards against a real production bug from years ago.
- If the original reason no longer applies, document the reasoning in the simplification commit. If you can't determine the reason, leave it alone — the cost of the fence is one read, the cost of a regression is much higher.
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 · 96 lines · 62 tokens per session scan A 215b44ad26cf
code-simplification is a skill published in the GitHub repository nexus-substrate/nexus-agents (18 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 1,289 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 2026-08-30.
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…