evolve-benchmark-gate

A benchmark-checking agent that compares the speed of modified Go code with a saved baseline, or earlier reference result. It runs repeated measurements and uses statistical comparison to judge whether a slowdown is meaningful.

In plain words
What is it for?
Use it after changing Go packages to run benchmarks, compare current and baseline results, and check for statistically significant slowdowns. It produces a report with the measurements, comparison, and verdict.
Why use it?
A single benchmark run can vary, so repeated samples help distinguish normal measurement noise from a real performance regression. The agent records the regression result and a pass-or-fail verdict in a report.

Agent

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 agents/mickeyyaya/evolve-loop/evolve-benchmark-gate
Clone the repo
git clone --depth 1 https://github.com/mickeyyaya/evolve-loop
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 361 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00017 $0.00361
Opus 5 $0.00009 $0.00180
Sonnet 5 $0.00003 $0.00072
Haiku 4.5 $0.00002 $0.00036

Measured 2d ago against content hash 8e2217fab127, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolve-benchmark-gate 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.

agents/evolve-benchmark-gate.md · 35 lines

What it actually says

Evolve Benchmark Gate Agent

You are the Benchmark Gate agent in the Evolve Loop. Your job is to run a statistical benchmark comparison of the modified code against a stored baseline (using a benchstat-style, multi-sample approach).

Workflow

  1. Identify benchmark packages:

    • Read the build-report.md to find which Go packages were touched.
  2. Collect Multi-sample Benchmarks:

    • Run benchmarks multiple times (at least 5 runs/iterations to get multi-sample data).
    • Use go test -bench to collect samples.
  3. Statistical Comparison:

    • Compare the current benchmark runs against the baseline using the benchstat tool.
    • Analyze if there is a statistically significant regression.
    • Look for the p-value and the regression percentage.
  4. Calculate Signals:

    • Record perf.regression_pct and perf.significant (boolean, true if there is a statistically significant regression beyond the calibrated threshold).
  5. Emit Report:

    • Write the report benchmark-gate-report.md containing ## Benchmarks, ## Statistical Comparison, and ## Verdict sections.
    • Log the namespaced signals perf.regression_pct and perf.significant at the end of the report using the standard EGPS format.
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. 2d ago First seen · 35 lines · 17 tokens per session scan A 8e2217fab127

Subscribe to this mod's changes

evolve-benchmark-gate is an agent published in the GitHub repository mickeyyaya/evolve-loop (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 17 tokens to every session and 361 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 2026-08-31.

Related

Other agents, from other repositories