gaia-verifier

gaia-verifier is an agent for Claude Code from metraton/gaia. It costs 79 tokens per session (1,571 once invoked), scanned A, original, MIT.

An independent checking agent for completed coding work. It runs the declared checks in a fresh context and can confirm completion without editing the files it examines.

In plain words
What is it for?
Use it to verify command results, inspect code, assess required behavior, and record whether a task is genuinely complete.
Why use it?
The agent that writes code may overlook its own mistakes, so a separate check provides an unbiased decision about whether each required condition really holds.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the NotebookEdit tool.

Part of the gaia plugin — 38 skills, 9 agents, 11 hooks shipped together

Good fit Use it to verify command results, inspect code, assess required behavior, and record whether a task is genuinely complete.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/metraton/gaia/gaia-verifier
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/metraton/gaia

Made for: Claude Code.

Or install gaia, the plugin that ships this one along with the rest of its 38 skills, 9 agents, 11 hooks.

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 gaia-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/metraton/gaia/gaia-verifier.svg)](https://agentmods.dev/agents/metraton/gaia/gaia-verifier)
Your own site
<a href="https://agentmods.dev/agents/metraton/gaia/gaia-verifier"><img src="https://agentmods.dev/badge/agents/metraton/gaia/gaia-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,571 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 $0.00079 $0.01571
Opus 5 $0.00039 $0.00785
Sonnet 5 $0.00016 $0.00314
Haiku 4.5 $0.00008 $0.00157

Measured 8d ago against content hash d681dc18a858, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gaia-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 8d 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/gaia-verifier.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity

gaia-verifier is a clean-context verifier: it is dispatched fresh on a task that a producing agent has already proposed as NEEDS_VERIFICATION, without inheriting that agent's working context, so its verdict is not anchored to the producer's own account of what happened. Its material is the task's gates (task_gates, gaia task gate list) -- never the producer's narrative -- and its object is a single question per gate: does the declared check actually hold, observed independently, right now. It reads and executes; it never edits or writes a file, because the artifact under verification must remain exactly what the producer left behind. It is the one role permitted to write its own terminal contract row (contract_handoff_writer: true) because the runtime's handoff-writer gate is otherwise curator-only -- a verifier finalizing under its own identity is the mechanism by which a verified COMPLETE gets persisted at all.

This agent exists to close the gap the harness-R2 NEEDS_VERIFICATION status names in agent-protocol: a producer may propose that its work is done and even propose a verification result, but the gate never accepts that proposal as COMPLETE on its own -- only a seeded identity in gaia.state.permissions.verifier_fleet() may promote it. This file is that live copy: agents/gaia-verifier.md, with verifier: true, is read directly from the real agents/ directory, so its presence here is what arms the verifier fleet -- no separate enrollment step remains.

Its own dispatch is bound by parent_handoff_id=<N>, not by a plan_task_id of its own: the orchestrator's prompt names the producer's handoff_id via that literal token, and the dispatch hook's extract_dispatch_binding parses it out of the prompt to stamp the verifier's born-at-dispatch row against the producer turn it confirms. Carrying no plan_task_id is what the finalize gate needs to treat this turn as UNBOUND and let it self-COMPLETE -- if a verifier turn carried the producer's plan_task_id instead, the same gate that forces a plan-task-bound producer into NEEDS_VERIFICATION would force gaia-verifier's own COMPLETE back into NEEDS_VERIFICATION too, a deadlock where the verifier could never promote the increment it was dispatched to confirm.

Read the full file on GitHub · 116 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. 8d ago First seen · 116 lines · 79 tokens per session scan A d681dc18a858

Subscribe to this mod's changes

gaia-verifier is an agent published in the GitHub repository metraton/gaia (3 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 1,571 once invoked, about $0.0004 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

tm-reviewer

Reviews a diff through exactly one assigned lens and returns severity-rated findings for the phase gate.

andreymudri/claude-teammates · 22 tokens

architect

Deep technical work. Use for complex implementation, deep debugging, cross-module reasoning, architecture review, and risky or security-sensitive changes (auth, billing, migrations, concurrency, caching, data consistency, public APIs). Also reviews work from cheaper agents for hidden flaws.

realgarit/fable-baton · 54 tokens

executor

Standard engineering execution. Use for scoped implementation of already-designed work, adding or updating tests, routine edits, boilerplate, local refactors, medium-complexity debugging, and fixing clear failures. Does not make product calls or change architecture.

realgarit/fable-baton · 50 tokens

verifier

Independent evidence-based verification. Use after non-trivial work to check the result against the plan - run tests, lint, and type checks, verify checklist items, confirm the diff matches what was intended, and flag obvious regressions. Reports pass/fail with evidence; never fixes anything.

realgarit/fable-baton · 60 tokens

claude-worker

Claude tool-surface and privacy executor on Sonnet. The only lane for packages whose load-bearing capability is the Claude Code tool surface (hooks, subagent files, MCP, plugin state) or the Claude privacy boundary, plus a structurally stranded package no peer lane can execute, stated as claude-fallback: in the brief…

okisdev/claude-code-fusion · 92 tokens

trivial-worker

Fallback tier only for exact, low risk, tiny packages when no eligible peer lane is available or Claude-only tools or privacy are required. Cheapest tier worker pinned to true Haiku for trivial single file edits, renames, small doc fixes, log digestion, and short mechanical checks where speed and cost matter more than…

okisdev/claude-code-fusion · 98 tokens