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 skills add HomenShum/NodeBenchAI --skill architecture-supersededgit clone --depth 1 https://github.com/HomenShum/NodeBenchAIWrote 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.
[](https://agentmods.dev/skills/homenshum/nodebenchai/architecture-superseded)<a href="https://agentmods.dev/skills/homenshum/nodebenchai/architecture-superseded"><img src="https://agentmods.dev/badge/skills/homenshum/nodebenchai/architecture-superseded/github.svg" alt="Measured on agentmods" height="20"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.
<a href="https://agentmods.dev/skills/homenshum/nodebenchai/architecture-superseded"><img src="https://agentmods.dev/badge/skills/homenshum/nodebenchai/architecture-superseded.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00116 |
| Opus 5.5 | $0.00000 | $0.00046 |
| Sonnet 5.5 | $0.00000 | $0.00023 |
| Haiku 4.5 | $0.00000 | $0.00012 |
Grade A, and why
architecture-superseded scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain,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 1mo 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
Skill: Flywheel UI Dogfood
This repo uses a continuous dogfood + QA loop for frontend changes.
See skills/flywheel-ui-dogfood/SKILL.md.
Additional workflow skills:
skills/agent-run-verdict-workflow/SKILL.mdfor contract wiring, backend verdict enrichment, live workflow panels, exact verdict surfacing, and verification on agent-run features.skills/owner-mode-end-to-end/SKILL.mdfor directing the agent like the accountable owner across contract, backend, UI, verification, and workflow documentation.
What ships with it
60 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.
- 2026-01-04-nodebench-ai-comprehensive-implementation-plan.md 6.8 KB
- AGENT_NATIVE_UI_MCP_COMPATIBILITY.md 3.2 KB
- AGENT_QUESTION_CATALOG.md 16 KB
- AGENT_TRUST_INFRASTRUCTURE.md 6.4 KB
- AI_FLYWHEEL.md 15 KB
- AMBIENT_INTELLIGENCE_LAYER.md 13 KB
- ANALYTICS_ROUTE_INTEGRATION.md 8.4 KB
- APP_SCORING_AND_DOGFOOD_INSTRUCTIONS.md 6.7 KB
- ARCHETYPE_GAP_ANALYSIS.md 12 KB
- ARCHITECTURE_HYBRID_DCF.md 13 KB
- ATTENTION_ENGINEERING_SPEC.md 16 KB
- ATTRITION_REDESIGN_SPEC.md 11 KB
- BACKGROUND_MODE_AND_RELIABILITY.md 12 KB
- CHANGELOG_2026-02-02_LINKEDIN_ORG_PAGE_ROUTING.md 5.0 KB
- COCKPIT_WIREFRAMES.md 24 KB
- CODEBASE_REVIEW_MAP_2026_03_19.md 23 KB
- CODEV_FINDINGS.md 3.4 KB
- COMPETITIVE_INTEL_MAR29.md 3.2 KB
- CONTINUOUS_OPTIMIZATION_PORTABLE_GUIDE.md 21 KB
- CONTROL_PLANE_90DAY_ROADMAP.md 10 KB
- CONVEX_NATIVE_SEARCH_SPEC.md 9.5 KB
- COST_ANALYSIS.md 8.2 KB
- DAILY_BRIEFING_MCP_UNIFIED_IMPLEMENTATION_PLAN.md 7.0 KB
- DAY1_USER_JOURNEYS.md 10.0 KB
- DCF_AGENT_ARCHITECTURE.md 36 KB
- DEEP_AGENT_OPTIMIZATION_GUIDE.md 17 KB
- DEEP_AGENTS_2.0_COMPLETE.md 10 KB
- DEEP_SIM_PRODUCT_SPEC.md 12 KB
- DEEP_VIRAL_DECONSTRUCTION.md 53 KB
- DEEPTRACE_DIMENSION_ENGINE_IMPLEMENTATION_SPEC.md 10 KB
- DELTA_SELF_DILIGENCE_SPEC.md 53 KB
- DEVELOPER_CODEBASE_MAP.md 19 KB
- DOGFOOD_RUNBOOK_V1.md 9.8 KB
- DOPAMINE_LOOP_AUDIT.md 19 KB
- DYNAMIC_PROMPT_ENHANCEMENT.md 13 KB
- ENHANCED_PROMPT_SYSTEM_V2.md 14 KB
- ENTITY_PAGE_FRAMEWORK_AUDIT.md 14 KB
- ENTITY_PAGE_REDESIGN.md 13 KB
- EXECUTION_BOARD.md 6.3 KB
- FEATURE_ROUTE_MAP.md 18 KB
- FINAL_CLEANUP_REPORT.md 5.1 KB
- FOUNDER_ARTIFACT_BUILD_PLAN.md 11 KB
- FOUNDER_CYCLE_ARCHITECTURE.md 8.3 KB
- FOUNDER_MCP_FLOW_SPEC.md 9.3 KB
- FOUNDER_PLATFORM_PRD.md 10 KB
- funding-detection-architecture.md 12 KB
- GATED_IMPROVEMENT_ARCHITECTURE.md 11 KB
- gemini-qa-flywheel-learnings.md 9.7 KB
- HACKATHON_MARKET_FIT_ANALYSIS.md 14 KB
- HARNESS_ARCHITECTURE_NEXT.md 3.2 KB
- HARNESS_V2_BUILD_PLAN.md 39 KB
- HARNESS_V2_ONE_PAGER.md 25 KB
- HARNESS_V2_PROPOSAL.md 95 KB
- HCSN_ARCHITECTURE.md 5.3 KB
- HYPERLOOP_SPEC.md 448 B
- IDEAFLOW_BLOCK_NOTEBOOK_ULTRAPLAN.md 28 KB
- IMPLEMENTATION_PLAN_GAP_CHECK.md 13 KB
- IMPLEMENTATION_PROGRESS.md 7.5 KB
- IMPLEMENTATION_SUMMARY.md 7.2 KB
- JIT_RETRIEVAL_LAYERED_MEMORY.md 7.3 KB
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.
- 1mo ago First seen · 10 lines · 0 tokens per session scan A 604d5f1ae4a2
architecture-superseded is a skill published in the GitHub repository HomenShum/NodeBenchAI (15 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 116 tokens. 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 2026-09-03.
Other skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
skill-release-gate
Evaluate an Agent Skill bundle for structural integrity, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity, and target-host portability before release.
typescript-testing
Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, Effect v4 CLI tests, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, validating TypeScript package changes, or writing/porting CLI tests against…
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
typescript-providers
Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google, LangChain, Mastra, Vercel, LlamaIndex, Cloudflare, Claude Agent SDK, and TypeSafe. Use for provider-specific TS work; do not use for core-only changes.