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/initnpx skills add brolag/neural-claude-code --skill initgit 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 | $0.00048 | $0.00601 |
| Opus 5 | $0.00024 | $0.00300 |
| Sonnet 5 | $0.00010 | $0.00120 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
init 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 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.
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.
What it actually says
/init — Generate Project CLAUDE.md
Scan the current project and generate a CLAUDE.md tailored to its stack and conventions.
Steps
1. Detect Stack
Check for these files (in order):
package.json→ Node.js (check for next, react, vue, angular, etc.)pyproject.tomlorrequirements.txt→ Pythongo.mod→ GoCargo.toml→ RustGemfile→ Rubypom.xmlorbuild.gradle→ Java/KotlinPackage.swift→ Swift
Read the detected config file to identify:
- Language and framework
- Test command (from scripts or conventions)
- Lint command
- Build command
2. Map Key Directories
Run ls at project root. Identify:
- Source code directory (src/, app/, lib/, etc.)
- Test directory (test/, tests/, tests/, spec/)
- Config files (tsconfig, eslint, prettier, etc.)
- API routes or endpoints
3. Check Existing Conventions
git log --oneline -10— commit message style- Check for existing CLAUDE.md, .cursorrules, .github/copilot-instructions.md
- Check for existing .editorconfig, prettier, eslint configs
4. Generate CLAUDE.md
Read the template from the neural-claude-code install directory. Replace placeholders:
{{PROJECT_NAME}}— from package.json name or directory name{{STACK_DESCRIPTION}}— detected stack summary{{LANGUAGE}}— primary language{{TEST_COMMAND}}— detected test command or "npm test"{{LINT_COMMAND}}— detected lint command or "npm run lint"{{DIRECTORY_MAP}}— key directories found
Write to CLAUDE.md in project root.
5. Report
Generated CLAUDE.md for [project name]
Stack: [detected stack]
Tests: [test command]
Lint: [lint command]
Review CLAUDE.md and adjust as needed.
Notes
- If CLAUDE.md already exists, ask before overwriting
- If stack can't be detected, generate a minimal template and ask user to fill in
- Never add secrets, API keys, or personal data to CLAUDE.md
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 · 68 lines · 48 tokens per session scan A e46182752b23
init is a skill published in the GitHub repository brolag/neural-claude-code (11 stars, last pushed 12d ago), licensed MIT. It adds 48 tokens to every session and 601 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…