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/helderberto/agent-skills/code-simplifynpx skills add helderberto/agent-skills --skill code-simplifygit clone --depth 1 https://github.com/helderberto/agent-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 | $0.00106 | $0.00804 |
| Opus 5 | $0.00053 | $0.00402 |
| Sonnet 5 | $0.00021 | $0.00161 |
| Haiku 4.5 | $0.00011 | $0.00080 |
Grade A, and why
code-simplify 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Simplify
Make working code clearer without changing what it does. Clarity over cleverness. Behavior is frozen — the test suite is the contract. Applies to frontend and backend equally.
Target: $ARGUMENTS (file, directory, or module — if blank, use unstaged changes)
Guardrails
- Chesterton's Fence — before removing anything, explain why it's there. If you can't, leave it and flag it. Never delete guards, checks, or branches you don't understand.
- Behavior is frozen — no functional changes. Green test suite before and after; if a test's meaning has to change, you've gone too far.
- Clarity over cleverness — a junior should read it without decoding. Prefer boring and obvious.
Workflow
1. Baseline
- Identify target files (blank → unstaged changes)
- Run the test suite. If red, stop — don't simplify broken code
- If a target has no tests, flag it: simplification is unverifiable without them (offer
/fortify)
2. Audit
List findings, most-impactful first:
| Smell | Simplification |
|---|---|
| Deep nesting (> 2 levels) | Guard clauses / early return |
| Dead code, unused params, unreachable branches | Delete (after Chesterton's Fence) |
| Duplicated logic | Extract one named helper |
| Clever one-liners, dense ternaries | Expand to readable form |
| Shallow pass-through wrapper | Inline it (/codebase-design — the deletion test) |
| Speculative flexibility / config never used | Remove |
| Unclear names, primitive obsession | Rename to intent |
Present the audit. Ask which items to apply — list each as an option, "All items" first and marked (Recommended). Use AskUserQuestion (multiSelect) when available; otherwise a numbered checklist.
3. Apply — one change at a time
Per approved item:
- Make the single change
- Run tests — must stay green
- If red → revert that change, flag as blocked
Never batch. Use immutable edits — introduce no new mutation.
4. Report
## Simplify Report
### Applied
- Flattened `parseConfig` — 4 nesting levels → guard clauses
- Deleted unused `legacyMode` param (Chesterton: git blame shows the feature was removed)
- Inlined `wrapResult` pass-through (deletion test: complexity vanished)
### Skipped / Blocked
- `retryLoop` — kept the sleep; couldn't confirm why (Chesterton's Fence)
### Result
Tests: 42 passed | 0 failed | behavior unchanged
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 · 80 lines · 106 tokens per session scan A d7dff3a18ca2
code-simplify is a skill published in the GitHub repository helderberto/agent-skills (13 stars, last pushed 11d ago), licensed MIT. It adds 106 tokens to every session and 804 once invoked, about $0.0005 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
code-review-and-quality
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
constraint-driven-development
Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-ignore or…
performance-optimization
Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.
api-and-interface-design
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
code-simplification
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now…