benchmark-optimization-loop

A measured process for making software faster, cheaper, or more efficient by testing multiple implementations. Each version is checked for correctness and compared using a chosen measure such as runtime, latency, throughput, memory, errors, or cost.

In plain words
What is it for?
Use it to optimize latency, throughput, runtime, memory use, error rates, or operating cost through repeatable benchmarks.
Why use it?
It replaces guesswork with evidence and prevents an optimization from being accepted when it is faster but incorrect or unreliable. It also keeps the number of experiments and their impact bounded.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/23ag1/completely/benchmark-optimization-loop
Any agent
npx skills add 23ag1/completely --skill benchmark-optimization-loop
Clone the repo
git clone --depth 1 https://github.com/23ag1/completely

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 540 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 91% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00041 $0.00540
Opus 5 $0.00020 $0.00270
Sonnet 5 $0.00008 $0.00108
Haiku 4.5 $0.00004 $0.00054

Measured yesterday against content hash 32ad49eec763, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

benchmark-optimization-loop 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.

Origin

This is a copy

91% identical to benchmark-optimization-loop — 28 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

research/ecc/skills/benchmark-optimization-loop/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Benchmark Optimization Loop

Use this skill to convert "make it 20x faster" or "try 50 recursive optimizations" into a bounded measured loop that can actually improve a system.

Required Baseline

Do not optimize until these exist:

  • the operation being optimized;
  • the correctness gate that must stay green;
  • the metric: wall time, p95 latency, rows/sec, cost/run, memory, error rate;
  • the current baseline;
  • the search budget: max variants, max time, max spend, max data impact.

If the user asks for an unrealistic target, keep the ambition but make the loop bounded and measurable.

Loop

  1. Measure the baseline.
  2. Identify bottlenecks from evidence.
  3. Generate variants that test one hypothesis each.
  4. Run variants with the same input shape.
  5. Reject variants that fail correctness, safety, or reproducibility.
  6. Promote the fastest safe variant.
  7. Codify the winning path in a script, command, test, config, or doc.
  8. Rerun the baseline and winner to confirm the delta.

Variant Table

Track variants like this:

Variant | Hypothesis | Command | Time | Correct? | Notes
baseline | current path | npm run job | 120s | yes | stable
batch-500 | fewer round trips | npm run job -- --batch 500 | 42s | yes | winner
parallel-8 | more workers | npm run job -- --workers 8 | 31s | no | rate limited

For recursive or hyperparameter work:

  • persist every run to a ledger;
  • compare against the prior accepted winner, not only the previous run;
  • keep a holdout or replay check;
  • stop when improvement is within noise, correctness fails, cost exceeds the budget, or the search starts changing more variables than it can explain.

Use phrases like "best measured safe variant" instead of "global optimum" unless the search space was actually exhaustive.

Promotion Gate

A variant cannot become the new default until:

  • correctness tests pass;
  • the performance delta is repeated or explained;
  • rollback is obvious;
  • the change is encoded in source control or a durable runbook;
  • the final summary includes exact commands and measurements.

Read the full file on GitHub · 70 lines

Changes

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.

  1. yesterday First seen · 70 lines · 41 tokens per session scan A 32ad49eec763

Subscribe to this mod's changes

benchmark-optimization-loop is a skill published in the GitHub repository 23ag1/completely (5 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 540 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to benchmark-optimization-loop, differing in 28 lines, and is treated as a copy.

Related

Other skills, from other repositories