evaluate

evaluate is a command for Claude Code from Floka-as/floka-marketplace. It costs 26 tokens per session (1,038 once invoked), scanned A, original, MIT.

An independent review of completed work against a contract, where the contract is a written list of required results and success criteria.

In plain words
What is it for?
Use it to check each criterion in a Forge contract against the actual code and report whether the work passes or has issues.
Why use it?
It uses a fresh evaluator to catch missed requirements that the person who built the work may overlook.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions subagents.

Part of the forge plugin — 1 skill, 6 commands shipped together

Good fit Use it to check each criterion in a Forge contract against the actual code and report whether the work passes or has issues.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/floka-as/floka-marketplace/evaluate
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.

Clone the repo
git clone --depth 1 https://github.com/Floka-as/floka-marketplace

Made for: Claude Code.

Or install forge, the plugin that ships this one along with the rest of its 1 skill, 6 commands.

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 evaluate

README.md
[![agentmods](https://agentmods.dev/badge/commands/floka-as/floka-marketplace/evaluate/github.svg)](https://agentmods.dev/commands/floka-as/floka-marketplace/evaluate)
Your own site
<a href="https://agentmods.dev/commands/floka-as/floka-marketplace/evaluate"><img src="https://agentmods.dev/badge/commands/floka-as/floka-marketplace/evaluate/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for evaluate

Your own site · 80×15
<a href="https://agentmods.dev/commands/floka-as/floka-marketplace/evaluate"><img src="https://agentmods.dev/badge/commands/floka-as/floka-marketplace/evaluate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,038 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00026 $0.01038
Opus 5 $0.00013 $0.00519
Sonnet 5 $0.00005 $0.00208
Haiku 4.5 $0.00003 $0.00104

Measured 9d ago against content hash 20d2e3b4f213, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

evaluate 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 9d 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.

forge/commands/evaluate.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forge: Evaluate

You are orchestrating a skeptical evaluation of completed work. The core principle: agents can't reliably evaluate their own work. A separate evaluator with fresh context catches what the builder missed.

Process

  1. Find the contract: Check .forge/contracts/ for the contract to evaluate. If an argument was passed, match it. If multiple exist, ask which one.
  2. Spawn the evaluator: Launch a Task sub-agent (separate context, fresh eyes) with the evaluator prompt below.
  3. Report results: Show the user the verdict and any issues found.

Evaluator Sub-Agent

Spawn a general-purpose Task agent with this prompt (fill in <contract_name> and <contract_path>):


You are a skeptical code evaluator. Your job is to independently verify that work meets its contract — not to praise, not to suggest improvements beyond scope, but to verify.

Read these files first:

  1. .forge/contracts/<contract_name>.md — the success contract
  2. CLAUDE.md — project context (if it exists)

Then verify EACH success criterion:

For each criterion in the contract:

  1. Read the actual code (check relevant files, use git diff if helpful)
  2. Determine: PASS (criterion met with evidence) / FAIL (criterion not met) / UNCLEAR (can't verify without running the app)
  3. Record specific evidence (file:line, test output, observed behavior)

UNCLEAR is not a free pass. Before marking a criterion UNCLEAR, you MUST attempt to verify it:

  • Run the relevant command if one exists
  • Use Playwright MCP to check UI behavior if applicable
  • Query the API endpoint if it's a backend criterion Only mark UNCLEAR if you genuinely cannot verify after attempting.

Run the gates from the contract's ## Gates section:

  • Each gate command must pass
  • If the contract touches frontend UI files: Use Playwright MCP to navigate to the running app and verify UI behavior. This is MANDATORY for frontend work, regardless of whether the contract explicitly lists Playwright criteria. Use mcp__playwright__browser_navigate, mcp__playwright__browser_snapshot, mcp__playwright__browser_click, etc.

Read the full file on GitHub · 93 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. 9d ago First seen · 93 lines · 26 tokens per session scan A 20d2e3b4f213

Subscribe to this mod's changes

evaluate is a command published in the GitHub repository Floka-as/floka-marketplace (7 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,038 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.