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/sdcorejs/sdcorejs-agent/sdcorejs-nextjsnpx skills add sdcorejs/sdcorejs-agent --skill sdcorejs-nextjsgit clone --depth 1 https://github.com/sdcorejs/sdcorejs-agentWhat 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 | $0.00097 | $0.04100 |
| Opus 5 | $0.00048 | $0.02050 |
| Sonnet 5 | $0.00019 | $0.00820 |
| Haiku 4.5 | $0.00010 | $0.00410 |
Grade A, and why
sdcorejs-nextjs 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Website — Write Code Orchestrator
Shared Protocols
Read _refs/shared/runtime-protocols.md and
_refs/shared/artifact-lifecycle.md; merge producer artifact_context through
the finishing tail.
Purpose
Single entry point for generating approved Next.js website code. This skill is the
dispatch layer between an approved plan from sdcorejs-execute-plan and the
focused REFERENCE PACKS that hold the per-concern generation rules. It does NOT
inline those rules — it reads the right pack on demand. The ten packs under
_refs/nextjs/build-website/write-code/ were standalone sub-skills before they
were consolidated here so the track exposes one orchestrator instead of eleven.
When invoked
- After
sdcorejs-execute-plandispatches an approved Next.js plan - After
sdcorejs-explore (recovery mode)and the user explicitly resumes the same approved plan
Do NOT invoke if:
- No plan exists or plan is unapproved -> go back to
sdcorejs-brainstorming/sdcorejs-spec/sdcorejs-plan - Scope changed since plan was approved -> re-plan with
sdcorejs-plan - The user wants to AUDIT an existing site (not generate) →
sdcorejs-review
Step 0 — Read-oriented project context
Before reading the plan or dispatching, assemble read-only project_context.
Use valid summary sections when available. For an existing site with a missing,
legacy, unknown, or stale summary, continue with targeted reads and use a scoped
code map only for unresolved cross-component relationships. Do not refresh
merely because summary is absent. A brand-new approved init-site may create
summary v2 after scaffolding; an architecture-level refresh belongs only to the
sequential workflow or integration owner.
Before generating any non-trivial page, section, interactive block, form, or
frontend data boundary, read _refs/shared/frontend-architecture.md. Require the
approved plan dispatched by sdcorejs-execute-plan to contain a completed
frontend_architecture contract. This executor must not create or self-approve a
missing contract. Stop and return to sdcorejs-plan through
sdcorejs-execute-plan when the gate is missing, incomplete, or contradicted by
current code evidence.
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 · 252 lines · 97 tokens per session scan A 569a05309078
sdcorejs-nextjs is a skill published in the GitHub repository sdcorejs/sdcorejs-agent (2 stars, last pushed 16d ago), licensed MIT. It adds 97 tokens to every session and 4,100 once invoked, about $0.0005 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 2026-08-31.
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…