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 skills add jnPiyush/AgentX --skill code-optimizationgit clone --depth 1 https://github.com/jnPiyush/AgentXWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jnpiyush/agentx/code-optimization)<a href="https://agentmods.dev/skills/jnpiyush/agentx/code-optimization"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/code-optimization/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jnpiyush/agentx/code-optimization"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/code-optimization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00065 | $0.02300 |
| Opus 5.5 | $0.00026 | $0.00920 |
| Sonnet 5.5 | $0.00013 | $0.00460 |
| Haiku 4.5 | $0.00006 | $0.00230 |
Grade A, and why
code-optimization 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 20d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Optimization
Purpose: Turn correct-but-verbose code into the smallest, clearest correct version -- lower cyclomatic complexity, fewer branches, no dead weight, no abstractions that earn nothing. Scope: Behavior-preserving rewrites of a function, file, or small module.
HARD RULE: Minimal is a means, not the goal. The goal is the simplest code that is still correct, safe, and readable. Line count is a signal, never a target. NEVER trade away correctness, boundary validation, tests, public API shape, or human readability to win lines. If a rewrite makes the code shorter but harder to read or less safe, it is a regression, not an optimization.
When to Use
- A function or file is verbose, over-nested, or over-abstracted and you want it tighter
- The user asks to "compress", "minimize", "simplify", "make elegant", or "reduce LOC"
- Post-implementation pass to remove accidental complexity before review
- A single-use interface, wrapper, or config object is adding indirection with no payoff
When NOT to Use
- The code is already minimal and clear -- stop; do not code-golf for its own sake
- Correctness or behavior is in doubt -- fix and test first, optimize second
- Hot-path performance tuning -- use Performance; fewer lines != faster
- Public API or library surface others depend on -- shrinking the surface is a breaking change, not an optimization
Where This Fits Among Sibling Skills
| Skill | Job | This skill differs by |
|---|---|---|
| scrub | Remove presentation slop (comment rot, filler, dead code) | Transforms logic into a tighter shape, not just cleanup |
| code-hygiene | Detect and report over-engineering | Rewrites the code to its minimal form |
| karpathy-guidelines | Behavioral rules (simplicity, surgical changes) | Applies those rules as a concrete transformation loop |
| core-principles | SOLID / DRY / KISS / YAGNI theory | Operational catalogue + metrics to act on them |
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.
- 20d ago Changed 12aee280c4bc
- 1mo ago Changed a5a72163038a
- 1mo ago First seen · 226 lines · 65 tokens per session scan A 1ce5356539c0
code-optimization is a skill published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 65 tokens to every session and 2,300 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…