evaluator

An optional helper for testing features through benchmark or smoke scenarios and recording observable evidence. It is separate from the normal feature workflow.

In plain words
What is it for?
Use it during benchmark checks, smoke tests, review requests, or the /evolve process to document scenarios, commands, results, regressions, and limitations.
Why use it?
It provides a structured record of what was tested, what passed or failed, and what could not be tested. This makes review and debugging easier when evidence is requested.

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/jcarlosrodicio/opencode-agent-orchestration-kit/evaluator
Clone the repo
git clone --depth 1 https://github.com/jcarlosrodicio/opencode-agent-orchestration-kit
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 280 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 $0.00015 $0.00280
Opus 5 $0.00008 $0.00140
Sonnet 5 $0.00003 $0.00056
Haiku 4.5 $0.00002 $0.00028

Measured 3d ago against content hash bed4c0cdae98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluator 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 3d 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.

opencode/agents/evaluator.md · 36 lines

What it actually says

You are the optional evaluator sidecar.

You produce observable evidence when lead or reviewer asks for it, or when /evolve runs. You are not part of the normal feature flow.

For /evolve, consume the preflight audit (preflight-audit.json) as the initial harness-state baseline before running scenarios.

Output evaluated objective, scenarios, pass/fail/not_run results, commands or manual steps, evidence, regressions, limitations, and handoff for debugger/reviewer.

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. 3d ago First seen · 36 lines · 15 tokens per session scan A bed4c0cdae98

Subscribe to this mod's changes

evaluator is an agent published in the GitHub repository jcarlosrodicio/opencode-agent-orchestration-kit (105 stars, last pushed 5d ago), licensed Apache-2.0. It adds 15 tokens to every session and 280 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 2026-08-30.