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/htmlnpx skills add brolag/neural-claude-code --skill htmlgit 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 | $0.00081 | $0.02690 |
| Opus 5 | $0.00041 | $0.01345 |
| Sonnet 5 | $0.00016 | $0.00538 |
| Haiku 4.5 | $0.00008 | $0.00269 |
Grade A, and why
html 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
html
Build a single-file, framework-free HTML artifact that makes a plan or a run report easy and calm to read. Two templates: PlanViewer (before executing) and ResultViewer (after finishing).
Always read references/principles.md before building. It holds the 10 anti-cognitive-fatigue principles with the reasoning behind each — follow the reasoning, not just the rule.
When to use
- The user explicitly asks for an "HTML artifact", a "plan/result view", a "dashboard", or to "show this as HTML".
- You are presenting a multi-phase plan/proposal/breakdown and the user wants it as a document.
- You just finished a multi-step task and the user wants a visual summary of what changed.
- The user wants a recap of a branch, commit, or PR diff (what a set of changes did), built from the real diff rather than from session memory.
When NOT to use
- A one-line answer, a single code snippet, or prose explanation.
- The user wants plain text or markdown only.
- Do NOT auto-fire on every plan.
/specand/discoverwrite Markdown only (Neural Codex contract). This skill is on-demand and standalone when the user asks for an HTML artifact.
1. Pick the template
- PlanViewer (pre-execution) →
templates/plan-viewer.html. Sections: Overview · Phases & Tasks · Decisions · Risks · Open Questions. - ResultViewer (post-execution) →
templates/result-viewer.html. Sections: Summary · Files Changed · Commands Run · Errors/Warnings · Next Steps.- Recap from a diff: point the ResultViewer at a branch, commit, or PR instead of the current session. Read the real change with read-only git (
git diff <base>...<ref>,git show <commit>,git log --stat) and fill Files Changed, per-file diffs, and stats from that output. Same template, the source is the diff. This is the reverse of a plan: it describes the change that was just made, one altitude above line-by-line review.
- Recap from a diff: point the ResultViewer at a branch, commit, or PR instead of the current session. Read the real change with read-only git (
If the user's intent is ambiguous (could be either), ask once; otherwise infer from tense ("show me the plan" → Plan, "what changed" → Result).
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 112 lines · 81 tokens per session scan A 55dfa67cbb0f
html is a skill published in the GitHub repository brolag/neural-claude-code (11 stars, last pushed 12d ago), licensed MIT. It adds 81 tokens to every session and 2,690 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 2026-08-30.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.