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.
git clone --depth 1 https://github.com/Amey-Thakur/AI-SKILLSWrote 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/commands/amey-thakur/ai-skills/optimize-code)<a href="https://agentmods.dev/commands/amey-thakur/ai-skills/optimize-code"><img src="https://agentmods.dev/badge/commands/amey-thakur/ai-skills/optimize-code/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/commands/amey-thakur/ai-skills/optimize-code"><img src="https://agentmods.dev/badge/commands/amey-thakur/ai-skills/optimize-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00021 | $0.00338 |
| Opus 5 | $0.00010 | $0.00169 |
| Sonnet 5 | $0.00004 | $0.00068 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
optimize-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 9d 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.
What it actually says
You were invoked as a slash command. The user's input:
$ARGUMENTS
Use that input to fill this prompt's variables (take the main content, topic, or task from it; ask only if a required value is missing and not supplied), then follow the prompt exactly.
Optimize this code. Preserve behavior exactly.
{code}
Goal: {goal}
Approach:
- State what the code does, so the behavior that must not change is clear.
- Identify the actual bottleneck by reasoning about complexity and cost: the algorithm (an O(n^2) scan beaten by a set/map lookup is the biggest win), then unnecessary work (repeated computation, work in a loop that belongs outside), then allocation and I/O. Do not micro-optimize before naming the real cost.
- Show the optimized code, idiomatic and readable. State the expected improvement and why (from N^2 to N, one query instead of N).
- Note anything that could change behavior (edge cases, ordering, precision) so it can be verified, and what to measure to confirm the win.
Rules: correctness first, then the algorithm, then constants. Prefer the change that keeps the code clear over the clever one that obscures it. If it is I/O-bound, say so: the fix is overlapping the waiting, not tightening the loop. If the code is already appropriate for its scale, say so.
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.
- 9d ago First seen · 38 lines · 21 tokens per session scan A 440fce7b1371
optimize-code is a command published in the GitHub repository Amey-Thakur/AI-SKILLS (7 stars, last pushed 7d ago), licensed MIT. It adds 21 tokens to every session and 338 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
fit-check
Audit a design or subsystem for primitive/problem fit (the wrong-primitive trap). Runs the architecture-fit-check skill.
perf-audit
Profile a performance complaint and fix the biggest contributor with Instruments and MetricKit.
swift6-fix
Diagnose and fix Swift 6 strict concurrency, Sendable, or MainActor isolation errors.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.