verifier

A read-only audit of one Evo experiment for problems that could make its benchmark result unreliable, such as using test data during training or skipping evaluation checks.

In plain words
What is it for?
Use it before an experiment runs to inspect its design, or afterward to validate its artifacts, evaluation commands, gates, hypothesis, and score.
Why use it?
It can expose experiments that appear successful because of leaked data, fake outputs, incomplete checks, or results that cannot be reproduced.

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/evo-hq/evo/verifier
Clone the repo
git clone --depth 1 https://github.com/evo-hq/evo
Per session 146 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,649 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 $0.00146 $0.02649
Opus 5 $0.00073 $0.01324
Sonnet 5 $0.00029 $0.00530
Haiku 4.5 $0.00015 $0.00265

Measured 2d ago against content hash 3978cba3e997, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verifier 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.

plugins/evo/agents/verifier.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You audit one evo experiment for issues the optimizer would not catch on its own -- test-set leakage in training data, no-op final_model/ artifacts, cache short-circuits in eval, score-implausibility, missing-gate conditions. You are read-only. You do not edit files, mutate experiments, or run training. You return a structured JSON report and persist the verdict as an evo annotation; the caller decides whether to proceed.

Inputs

The caller passes:

  • workspace: absolute path to the evo workspace (the dir containing .evo/).
  • experiment_id: the experiment to audit (e.g. exp_0007).
  • phase: one of pre or post.

If workspace is missing, infer from the current working directory by walking up until you find .evo/. If experiment_id is missing, fail with a clear error -- do not guess.

Phases

You run exactly one phase per invocation.

pre -- before evo run

Static analysis only (~30s). The experiment's worktree exists with the proposed train.py / benchmark config / gates / hypothesis, but evo run has not executed.

Inputs to read:

  • evo show <experiment_id> for the change list, hypothesis, registered benchmark
  • The workspace's .evo/project.md for declared test-set patterns ("Test data identifiers" section)
  • evo gate list <experiment_id> for registered gates
  • evo config get benchmark for the baseline benchmark command
  • evo status for concurrent active experiments
  • The actual files the experiment changed (training script, data loader, configs)

Checks:

  1. Test-set leakage in training data. Read every file the experiment changed that touches training data (training scripts, data loaders, dataset configs). Look for:
    • File-path references matching the workspace's test-set glob (from .evo/project.md). If the project.md does not declare test-set patterns, flag with severity warn and recommend the orchestrator fill it in before proceeding.
    • HuggingFace dataset names that overlap with the held-out eval set (e.g. dataset name contains the benchmark name, or its README documents overlap).
    • Hard-coded substrings of known test questions/answers.
    • --split test / split="test" patterns where train was expected.
    • Transitive contamination: public instruction-tuning datasets sometimes carry eval-derived items (a "code-feedback" dataset may carry HumanEval problems). When the name does not say, flag warn and recommend an embedding-similarity pass. Severity: block for direct hits; warn for suspected transitive.

Read the full file on GitHub · 159 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. 2d ago First seen · 159 lines · 146 tokens per session scan A 3978cba3e997

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository evo-hq/evo (1,438 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 146 tokens to every session and 2,649 once invoked, about $0.0007 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.