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 kensaurus/cursor-kenji --skill audit-langfuse-llmgit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/audit-langfuse-llm)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/audit-langfuse-llm"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/audit-langfuse-llm/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/kensaurus/cursor-kenji/audit-langfuse-llm"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/audit-langfuse-llm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 9 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 170 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 188 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 194 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 219 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 236 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 255 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 266 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 298 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 284 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00073 | $0.03964 |
| Opus 5.5 | $0.00029 | $0.01586 |
| Sonnet 5.5 | $0.00015 | $0.00793 |
| Haiku 4.5 | $0.00007 | $0.00396 |
Grade A, and why
audit-langfuse-llm 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 28d 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 — 469 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Langfuse LLM Quality Audit
Degree of freedom: MIXED — Phases 0–1, 4 [HIGH freedom]; Phases 2–3
CLI traces and playwright [LOW freedom — run exactly]. Read
protocol-browser-anti-stall before any browser step. Phase 0 first: Phases 2–3 verify the feature map it produces.
How to reason
- Observe — quote the trace, prompt version, token/cost, or live output
- Interpret — is quality, cost, or the pipeline actually broken?
- Classify — missing-trace / prompt / cost / eval / grounding / correct
- Severity — pipeline break or untraced prod feature = P0; cost/eval gap = P1
Worked example
Observe: after Playwright chat,
langfuse-cli api traces listshows no new row;app/api/chat/route.tscallsopenai.chatwith no Langfuse wrap. Interpret: the live path is uninstrumented — the static map was wrong. Classify: missing instrumentation (pipeline break). Severity: P0 — prod chat is invisible. Finding: chat | P0 | no trace after live send | wrap the SDK call.
Self-critique before reporting [LOW freedom — do not skip]
- Concrete numbers — model + $/call or tokens, not "costs seem high"
- Live, not static — trigger the feature; missing post-trigger trace = P0
- Severity justified — P0 = pipeline break or untraced user-facing call
- Right owner — jailbreak/OWASP →
audit-llm-security; token caps →plan-llm-cost-guardrails - Keys stay in env — report host + presence, never secret values
Phase 0: Auto-Detect Langfuse Integration
0a. Find Langfuse Configuration
Search for environment variables and config files (in order):
.env,.env.local,.env.production— look forLANGFUSE_PUBLIC_KEY,LANGFUSE_SECRET_KEY,LANGFUSE_BASE_URL,LANGFUSE_HOSTlangfuse.config.ts,langfuse.config.js— dedicated config filesinstrumentation.ts/instrumentation.js— Next.js instrumentation with Langfuse- Supabase Edge Functions —
Glob("**/supabase/functions/**/index.ts")and search forLangfuseimports
What ships with it
1 file 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.
- 28d ago Changed · -13 tokens per session a29fefa66db6
- 1mo ago Changed · -7 tokens per session 304c01691838
- 1mo ago Changed e734024d75c9
- 1mo ago First seen · 469 lines · 93 tokens per session scan A 5f38b593d45e
audit-langfuse-llm is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 26d ago), licensed MIT. It adds 73 tokens to every session and 3,964 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
firebase-ai
Use when setting up firebaseai, generating text/chat with Gemini, streaming AI output, building multimodal prompts, or handling AI errors.
llm-application-dev
Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.
prompt-engineering
A set of rules for managing AI prompts and cleaning user input before it is placed into a prompt. Prompt injection is an attempt to make an AI ignore its intended instructions or perform an unintended action.
amazon-bedrock
Builds generative AI applications on Amazon Bedrock. Use when invoking models (Converse vs InvokeModel), building RAG with Knowledge Bases, creating Bedrock Agents, applying Guardrails, deploying to AgentCore, or migrating a Bedrock Agent (including inline agents) to an AgentCore Harness. Also for prompt caching…
embedding-pipeline-builder
Builds document embedding pipelines with text chunking, embedding generation, indexing, and retrieval optimization. Use when users request "embedding pipeline", "document indexing", "text chunking", "RAG preprocessing", or "semantic indexing".
langchain-workflow-builder
Builds LLM applications with LangChain including chains, agents, memory, tools, and RAG pipelines. Use when users request "LangChain setup", "LLM chain", "AI workflow", "conversational AI", or "RAG pipeline".