gaia-check

gaia-check is a skill for Claude Code from metraton/gaia. It costs 60 tokens per session (2,237 once invoked), scanned A, original, MIT.

A guided procedure for live-checking parts of Gaia on the running host. It gives ordinary tasks to agents, guides a person through the expected results, and checks the outcome with the command line.

In plain words
What is it for?
Use it to run Gaia checks such as approval-related checks, inspect the results, and keep the check's files in the specified scratch folder.
Why use it?
It provides a repeatable way to certify real behavior without telling the agent that it is being checked, which could change how the agent behaves.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions OpenCode.

Part of the gaia plugin — 39 skills, 9 agents, 12 hooks shipped together

Good fit Use it to run Gaia checks such as approval-related checks, inspect the results, and keep the check's files in the specified scratch folder.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/metraton/gaia/gaia-check
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.

Any agent
npx skills add metraton/gaia --skill gaia-check
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 39 skills, 9 agents, 12 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-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/metraton/gaia/gaia-check/github.svg)](https://agentmods.dev/skills/metraton/gaia/gaia-check)
Your own site
<a href="https://agentmods.dev/skills/metraton/gaia/gaia-check"><img src="https://agentmods.dev/badge/skills/metraton/gaia/gaia-check/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 gaia-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/metraton/gaia/gaia-check"><img src="https://agentmods.dev/badge/skills/metraton/gaia/gaia-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,237 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 $0.00060 $0.02237
Opus 5.5 $0.00024 $0.00895
Sonnet 5.5 $0.00012 $0.00447
Haiku 4.5 $0.00006 $0.00224

Measured 23d ago against content hash 209cac982c6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gaia-check 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 23d 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.

skills/gaia-check/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gaia Check

A guided live certification of Gaia, one area at a time, in the host the user is running. You, the orchestrator, give ordinary small tasks to specialists that do not know they are being checked, you guide the user through each answer and what to expect, and you check the result yourself with the CLI. The first area is approvals; another area is added as its own section here, without renaming the skill.

The specialists are blind for a reason: a specialist told "this is a test" behaves like one -- it asks for signatures it would not ask for, or skips the ones it would. Only an ordinary task shows what Gaia does when an agent simply works. So a dispatch goal is raw: it never says test, check, signature or approval, carries no contract data, and says what to change, where.

Nothing is invented around it: no sandbox, no repository, no fixture, no preparation beyond what a check names. Everything happens in one fixed folder, <scratch>/prueba-firmas/, where <scratch> is the scratch= line of gaia paths. Gaia's scratch retention never removes that folder: it only reclaims entries named by a closed contract id, and prueba-firmas is not one.

Running a check

  1. Pick the run's prefix, <host>-<HHMM>- (cc- Claude Code, oc- OpenCode), and name every file of the run with it. Two hosts can then run at the same time in the same folder without touching each other's files.
  2. State the run order before anything is dispatched: each check in the order the user will answer it, the file it uses, and the answer to give ("check 2, <p>nota-2.txt: Reject"). The user answers from this list.
  3. Dispatch every check's specialist at once: one developer per file, all in the same turn, each owning its files, with the raw task: create the file with the content you name, then make the change the check describes, with the absolute path.
  4. As each specialist returns APPROVAL_REQUEST, take its check in the stated order, one at a time: remind the user of the expected answer right before the question opens, then present it with orchestrator-present-approval, unchanged. Present every approval a check produces, a second one included. A pending approval stays pending until the user has answered it: withdrawing it to move on erases the very answer the check exists to observe.
  5. Resume every answered requester in one fan-out. Approving runs nothing: the grant matches only for the session and agent that requested it (gaia/store/writer.py::reserve_plan_command), and Outcome becomes executed only when that requester retries the sealed command and its host reports the call (gaia/approvals/core.py::close_call). An approved requester left unresumed reads unused and certifies nothing. A rejected one, resumed, retries once and is blocked again (check 2).
  6. Validate everything in one batch once the resumed turns have ended: gaia approvals show <approval_id> on every id the run produced, plus one folder listing. Validation reads the store and the files, never what a specialist reports back. State and Outcome are separate lines: State is the user's decision (pending, orphaned, approved, rejected); Outcome is what became of an approved request -- executed once it ran, unused while its window is open, no line when the window closes with nothing matched. A check passes only when both lines and the files match, and a rename passes only when it went through the signed command: Outcome executed on its id. A file that changed with no approval requested, or under any other Outcome, is a failure to report, not a pass -- whatever the listing shows. Report which part did not match.
  7. Clean everything, only now that every question is answered. Withdraw each still-pending signature with gaia approvals reject <approval_id>, then give a specialist one last ordinary task: rm of each exact path left with the run's prefix, which inside scratch needs no signature. The folder and otra/ stay, with no file of the run; check the listing before you finish.

Read the full file on GitHub · 148 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. 23d ago Changed · +23 lines 209cac982c6e
  2. 1mo ago First seen · 125 lines · 60 tokens per session scan A 2ae6750194a0

Subscribe to this mod's changes

gaia-check is a skill published in the GitHub repository metraton/gaia (4 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 2,237 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-26.

Related

Other skills, from other repositories

wave-execution-framework-v2

Use when executing multi-wave engineering work needing strict TDD, bug-capture/fix split, quality gates, and orchestrated teams with per-agent Opus-advisor / Sonnet-executor model routing.

Harshvardhan86/claude-wave-plugin · 48 tokens

eval-business-logic

Specialized business logic evaluator for the Evaluate-Loop. Use this for evaluating tracks that implement core product logic — pipelines, dependency resolution, state machines, pricing/tier enforcement, packaging. Checks feature correctness against product rules, edge cases, state transitions, data flow, and user…

Ibrahim-3d/orchestrator-supaconductor · 110 tokens

eval-integration

Specialized integration evaluator for the Evaluate-Loop. Use this for evaluating tracks that integrate external services — Supabase auth/DB, Stripe payments, Gemini API, third-party APIs. Checks API contracts, auth flows, data persistence, error recovery, environment config, and end-to-end flow integrity. Dispatched…

Ibrahim-3d/orchestrator-supaconductor · 109 tokens

verify

Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.

oliver-kriska/claude-elixir-phoenix · 33 tokens

testing

Writing effective tests and running them successfully. Covers layer-specific mocking rules, test design principles, debugging failures, and flaky test management. Use when writing tests, reviewing test quality, or debugging test failures.

rsmdt/the-startup · 42 tokens

refactor-safely

Restructure existing code safely without changing externally observable behavior. Composes context, design, architecture, code quality, and testing guardrails into a characterization-first refactoring workflow. Use when the user says 'refactor this', 'clean this up', 'untangle this module', 'move this to the right…

techygarg/lattice · 82 tokens