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.
npx agentmods add skills/brolag/neural-claude-code/exercisenpx skills add brolag/neural-claude-code --skill exercisegit clone --depth 1 https://github.com/brolag/neural-claude-codeWhat 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 | $0.00066 | $0.01005 |
| Opus 5 | $0.00033 | $0.00502 |
| Sonnet 5 | $0.00013 | $0.00201 |
| Haiku 4.5 | $0.00007 | $0.00101 |
Grade A, and why
exercise scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(npm *), Bash(npx *), Bash(pytest *), Bash(cargo *), Bash(go *), Bash(python *), Bash(node *), Bash(curl *), Read, Glob, Grep How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exercise
Verify that the changed product works for a user. Tests answer whether code checks pass. Exercise answers whether the promised workflow is usable end to end.
This skill is the Claude Code port of the Neural Codex exercise gate. Same contract, slash invocation. Default backend is CLI/HTTP so the kit runs with no extra MCP.
1. Select the backend
Detect the changed surface:
- CLI, TUI, installer, or scripts: terminal interaction
- web application or HTTP service:
curlagainst local endpoints by default. Isolated browser automation only if MCP tools are present and the assertion is visual - desktop application: computer-use automation if available
- documentation-only workflow: follow the documented commands in an isolated fixture and inspect the rendered or generated result
If browser or computer-use MCP is NOT available, do not block. Fall back to the test suite + CLI/HTTP path and say so in the report.
Ask for launch details only when they cannot be derived safely from repository scripts or documentation.
2. Run automated tests first
Detect and run the repository's normal test command. Record pass/fail counts and warnings. A failing suite makes the exercise verdict FAIL. Do not hide it behind a successful manual scenario.
If no test suite exists, record Tests: none found as a caveat.
3. Derive concrete scenarios
When --spec <plan> is supplied, turn its when/requires/ensures acceptance into one to three user flows. Otherwise derive flows from the user request and changed documentation.
Before reading the plan or selecting an evidence directory, resolve the repository root, the repository's plans/ directory, and the candidate spec. Require os.path.commonpath([candidate, plans_root]) == plans_root and reject escaping symlinks. Reject ../../outside/plan.md, plans/../outside/plan.md, /tmp/external-plan.md, and equivalent traversal. Without --spec, resolve exercise-evidence/ beneath the repository root and apply the same containment check before writing.
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.
- 2d ago First seen · 96 lines · 66 tokens per session scan A b8b06cc6ec06
exercise is a skill published in the GitHub repository brolag/neural-claude-code (11 stars, last pushed 12d ago), licensed MIT. It adds 66 tokens to every session and 1,005 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
test-conversion
Workflow for converting unit tests to browser tests for Project Bedrock. Invoke this when the user wants to remove complex Browser dependencies from tests.
agui-dotnet-cross-language-tests
Author cross-language interop tests that verify the AG-UI .NET SDK is wire-compatible with the TypeScript SDK — a Vitest TS client driving a C# CrossLanguage.TestServer over HTTP, both directions, including protobuf byte-parity against @ag-ui/proto. USE FOR: adding or modifying cross-language interop coverage…
cli-e2e-testcase-writer
Use when adding or updating Go CLI E2E coverage for one tests/clie2e/{domain} domain of the compiled lark-cli, especially when the work requires live --help or schema exploration, scenario-based clie2e.RunCmd workflows, and per-domain coverage.md maintenance.
harness-test-writer
Add regression test cases to the Bifrost provider harness (the Postman collection run via make run-provider-harness-test) based on a merged PR or a GitHub issue. Fetches the PR/issue, traces the affected wire path in the codebase, checks existing harness coverage, designs cases following harness conventions, inserts…
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.