A self-check skill for the Braina plugin and its supporting software. It checks installed versions, whether processing can use the CPU or GPU, the tool connection, and a full test with simulated data.

It is for checking, testing, and debugging a Braina installation and its neural-analysis tools.

It helps identify whether a failed or unavailable Braina tool is caused by the environment, missing dependencies, a disconnected server, or a slow first setup.

check — Skill for Claude Code by brainets/braina

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add brainets/braina

Claude Code

/plugin install braina

Made for: Claude Code.

Or install braina, the plugin that ships this one along with the rest of its 5 skills, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/brainets/braina/check/github.svg)](https://agentmods.dev/skills/brainets/braina/check)

Your own site

<a href="https://agentmods.dev/skills/brainets/braina/check"><img src="https://agentmods.dev/badge/skills/brainets/braina/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/brainets/braina/check"><img src="https://agentmods.dev/badge/skills/brainets/braina/check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 632 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.

Model	Per session	Once invoked
Fable 5.1	$0.00085	$0.00632
Opus 5.5	$0.00034	$0.00253
Sonnet 5.5	$0.00017	$0.00126
Haiku 4.5	$0.00009	$0.00063

Measured 29d ago against content hash b29582be1a53, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 29d 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.

plugin/skills/check/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Braina self-check

Run these steps in order and report the outcome plainly.

1. Smoke test (environment + tools)

uv run "${CLAUDE_PLUGIN_ROOT}/scripts/smoke_test.py"

Prints the Frites / HOI / NumPy versions and the JAX backend, then runs frites_sim_ar -> frites_conn_covgc -> frites_conn_net, hoi_oinfo -> hoi_get_nbest_mult, and plot_result on simulated data.
Ends with SMOKE TEST PASSED (exit 0) or SMOKE TEST FAILED: [...].
The first run after an install downloads ~150 MB of wheels and can take a few minutes; that is expected. Later runs take seconds.

2. If the braina MCP server did not connect

A CONNECTION_CLOSED / "Connection closed" status for the braina server at session start almost always means the cold start exceeded Claude Code's 30 s MCP timeout while uv was still downloading dependencies. Fix:

uv sync --script "${CLAUDE_PLUGIN_ROOT}/mcp/braina_mcp.py"

then reconnect with /mcp (or restart the session). The plugin's SessionStart hook runs this sync in the background automatically, so the second session normally works without intervention. If uv itself is missing: https://docs.astral.sh/uv/getting-started/installation/

3. Interpret the JAX line

JAX backend: CPU - the default; HOI tools run on CPU. Fine for a handful of ROIs and maxsize <= 4-5.
JAX backend: GPU - only happens if the user installed a CUDA-enabled jax in the environment uv resolves. Braina's own dependency block requests plain (CPU) jax; see the hoi-metrics skill, section "Compute backend", before promising GPU speed-ups.

4. Optional: full test suite (development checkout only)

From a clone of the braina repository:

uv run tests/run_tests.py

runs the pytest suite that exercises all 34 MCP tools on synthetic data.

Reporting

State: versions, backend, whether the smoke test passed, and - if it did not - the first failing tool and its error line verbatim. Do not describe the installation as working until the smoke test has actually passed.

Read the full file on GitHub · 62 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.

29d ago First seen · 62 lines · 85 tokens per session scan A b29582be1a53

Subscribe to this mod's changes

check is a skill published in the GitHub repository brainets/braina (5 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 85 tokens to every session and 632 once invoked, about $0.0003 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 2026-09-19.

Debugging Testing

systematic-debugging

4-phase root cause debugging: understand bugs before fixing.

NousResearch/hermes-agent · 16 tokens

langsmith-observability

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

davila7/claude-code-templates · 45 tokens

test-failure-explorer

Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.

QwenLM/qwen-code · 32 tokens

experimental-code-coverage-local-debugger

Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.

chromium/chromium · 59 tokens

verify-omnigent

Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…

omnigent-ai/omnigent · 100 tokens

cli-e2e

Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.

ComposioHQ/composio · 62 tokens