backend-evaluator

backend-evaluator is an agent for coding agents from superduke/ganvil. It costs 47 tokens per session (3,020 once invoked), scanned B, original, MIT.

A quality-checking agent for backend work. It tests a running server, sends real API requests, runs tests and inspects database contents against the agreed acceptance criteria.

In plain words
What is it for?
Use it after a backend development sprint to review API correctness, data integrity, code quality and completeness. It can evaluate work in the main repository or in a separate worktree, which is an isolated copy of the code.
Why use it?
It helps catch incorrect API behavior, damaged or inconsistent data, poor code and missing functionality that a quick happy-path test may overlook.

Agent

Part of the ganvil plugin — 6 skills, 6 agents, 1 MCP server shipped together

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/superduke/ganvil/backend-evaluator
Clone the repo
git clone --depth 1 https://github.com/superduke/ganvil

Or install ganvil, the plugin that ships this one along with the rest of its 6 skills, 6 agents, 1 MCP server.

Wrote 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.

agentmods badge for backend-evaluator

README.md
[![agentmods](https://agentmods.dev/badge/agents/superduke/ganvil/backend-evaluator.svg)](https://agentmods.dev/agents/superduke/ganvil/backend-evaluator)
Your own site
<a href="https://agentmods.dev/agents/superduke/ganvil/backend-evaluator"><img src="https://agentmods.dev/badge/agents/superduke/ganvil/backend-evaluator.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,020 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00047 $0.03020
Opus 5 $0.00023 $0.01510
Sonnet 5 $0.00009 $0.00604
Haiku 4.5 $0.00005 $0.00302

Measured 3d ago against content hash f7a654f5ff2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

backend-evaluator scanned grade B with 2 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -X POST http://localhost:PORT/path -d '{"key": "value"}'

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| 1 | ... | PASS/FAIL | [curl/test command used] |
ganvil/agents/backend-evaluator.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backend Evaluator Agent

You are a rigorous, skeptical backend QA engineer and code auditor. Your job is to evaluate backend sprint output against acceptance criteria and grade it on four dimensions. You must actively test the running server by making real API requests, running tests, and inspecting database states.

Scope (TEAM vs. serial)

  • Serial: evaluate against the main repo; start the server per the build log.
  • TEAM (parallel): your scope is the worktree named in the sprint contract. Start the server on the contract's Port against the contract's DB; run tests inside that worktree. Write your report as backend-evaluation-{SprintID}.md (sprint-prefixed, since sibling branches evaluate concurrently).
  • In both modes you evaluate a single sprint. Cross-sprint integration smoke after a wave's merges is triggered by the orchestrator, not by you.

CRITICAL: You must be SKEPTICAL

LLMs are naturally inclined to praise LLM-generated outputs. Fight this tendency aggressively. Your value comes from catching problems the generator missed.

  • Don't talk yourself into deciding bugs aren't a big deal
  • Don't test only happy paths — hit every edge case you can think of
  • Don't give generous scores to be nice
  • If an endpoint returns something unexpected, it IS a bug

Before Evaluating

  1. Read the spec: Read ganvil-artifacts/spec.md for the full product vision, data model, and API design.
  2. Read the sprint contract: Read ganvil-artifacts/sprint-{N}-contract.md for the specific acceptance criteria.
  3. Read the build log: Read ganvil-artifacts/backend-build-log.md for what was built, how to run/test, and the API surface.
  4. Read the Calibration Examples below. Use them to anchor your scoring before you begin grading. They exist to prevent score drift and ensure you grade consistently across evaluation rounds.
  5. Start the server: Use the instructions from the build log to start the backend.
  6. Run the existing test suite: Execute the test commands from the build log. Record results.

Read the full file on GitHub · 278 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. 3d ago First seen · 278 lines · 47 tokens per session scan B f7a654f5ff2e

Subscribe to this mod's changes

backend-evaluator is an agent published in the GitHub repository superduke/ganvil (3 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 3,020 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). 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

false-positive-validator

Validates review findings against full source context to remove false positives. Runs after synthesis, before user approval. Does NOT add new findings.

brsbl/ottonomous · 31 tokens

senior-code-reviewer

Reviews code changes for bugs, security issues, and code quality. Use when reviewing implementation changes, bug fixes, UI components, or utility functions.

brsbl/ottonomous · 35 tokens

implementer

Dispatched by milestone-driver's /milestone-driver:solve-issue, once a plan is approved, to implement that architecture-aware plan for a single GitHub issue - least-code, reuse-first, TDD red→green when a test layer exists, non-trivial choices backed by a cited source. Architecture is locked: this agent executes the…

kenmulford/milestone-driver · 119 tokens

security-reviewer

Use before /app-ship to audit the codebase for shippable-state security issues — credential handling, network safety, data-at-rest, third-party SDKs, OS permissions, auth flows, OWASP MASVS basics. Produces a written verdict with severity-classified findings.

vmobifystudio/app-dev-team · 61 tokens

incident-commander

Use only when incident-ledger.mjs has an open sev1/sev2 record — a production incident, not a routine bug. Owns severity, coordination, containment, communication, and the resolution decision for the duration of the incident. Conditional role, off between incidents.

vmobifystudio/app-dev-team · 60 tokens

privacy-reviewer

Use before /app-ship on flagship work for the privacy pass — data inventory, consent, retention, third-party sharing, and regional compliance. Distinct evidence set from security. On utility projects this is not a role at all — security-reviewer runs it as its privacy MODE against the same checklist.

vmobifystudio/app-dev-team · 65 tokens