agentmods.dev

claude-forge: Skill for Claude Code

.claude/skills/wire-langfuse/SKILL.md

wire-langfuse is a skill for Claude Code from arunanksharan/claude-forge. It costs 87 tokens per session (630 once invoked), scanned A, original, Unlicense.

A setup guide for Langfuse, a service that records and evaluates how an application uses large language models (LLMs). It covers Python and TypeScript applications and several common LLM frameworks.

In plain words
What is it for?
Use it when adding LLM tracing, output scoring, prompt management, or evaluation datasets to an application.
Why use it?
It helps developers track prompts, responses, usage, costs, feedback, and prompt versions in one place.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is arunanksharan/claude-forge's own configuration. It tells Claude Code how to work on claude-forge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-forge configures →

not rated 2repo 4mo ago A scan 87 tokens original Unlicense
View source ↗ arunanksharan/claude-forge
Reuse

Borrowing it

Nothing to install: this file belongs to arunanksharan/claude-forge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/arunanksharan/claude-forge/main/.claude/skills/wire-langfuse/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/arunanksharan/claude-forge

Made for: Claude Code.

Wrote 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.

agentmods badge for wire-langfuse

README.md
[![agentmods](https://agentmods.dev/badge/skills/arunanksharan/claude-forge/wire-langfuse/github.svg)](https://agentmods.dev/skills/arunanksharan/claude-forge/wire-langfuse)
Your own site
<a href="https://agentmods.dev/skills/arunanksharan/claude-forge/wire-langfuse"><img src="https://agentmods.dev/badge/skills/arunanksharan/claude-forge/wire-langfuse/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.

agentmods 80×15 button for wire-langfuse

Your own site · 80×15
<a href="https://agentmods.dev/skills/arunanksharan/claude-forge/wire-langfuse"><img src="https://agentmods.dev/badge/skills/arunanksharan/claude-forge/wire-langfuse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 630 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00087 $0.00630
Opus 5 $0.00044 $0.00315
Sonnet 5 $0.00017 $0.00126
Haiku 4.5 $0.00009 $0.00063

Measured 8d ago against content hash f7cde51a6f82, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

wire-langfuse 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 8d 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.

.claude/skills/wire-langfuse/SKILL.md · 33 lines

What it actually says

Wire Up Langfuse for LLM Observability (claudeforge)

Follow observability/04-langfuse.md. Steps:

  1. Confirm with user:
    • Stack: Python or Node/TS?
    • Hosting: Langfuse Cloud (default) or self-hosted?
    • Existing LLM framework: raw OpenAI / Anthropic SDK, LangChain, LlamaIndex, or Vercel AI SDK?
    • Have keys (LANGFUSE_PUBLIC_KEY, LANGFUSE_SECRET_KEY, LANGFUSE_HOST)?
  2. Install + configure the SDK:
    • Python: uv add langfuse + create langfuse_client.py with the Langfuse instance
    • Node: pnpm add langfuse + create langfuse.ts exporting the client
  3. Instrument LLM calls:
    • Use @observe() decorator (Python) or manual trace.generation() (Python/TS) for each LLM call
    • Pass model, input, output, usage (input/output tokens)
    • Add user_id, session_id, metadata (prompt version, feature flag) for filtering
  4. Set up integrations if relevant:
    • LangChain: CallbackHandler from langfuse — pass to chain.invoke({}, config={'callbacks': [handler]})
    • LlamaIndex: similar callback
    • Vercel AI SDK: LangfuseExporter via @vercel/otel
  5. Add scoring: capture user feedback (thumbs up/down) and send via langfuse.score(...). Inline scores for hallucination/quality if you have heuristics.
  6. Set up prompt management (optional but high-leverage): move static prompts into Langfuse, fetch via langfuse.get_prompt(name, label='production', cache_ttl_seconds=300). Lets non-engineers iterate.
  7. Build a baseline eval dataset: create dataset from production traces (langfuse.create_dataset_item(...)); use to compare prompt versions.
  8. Configure flushing: call langfuse.flush() in shutdown handler / FastAPI lifespan / process.on('SIGTERM').
  9. Scrub PII in inputs before passing to Langfuse if needed. Set sample rate for high-traffic apps.

Verify in the Langfuse UI: traces, completions, costs visible. Set up alerts on cost / failure rate if available.

Changes

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.

  1. 8d ago First seen · 33 lines · 87 tokens per session scan A f7cde51a6f82

Subscribe to this mod's changes

wire-langfuse is a skill published in the GitHub repository arunanksharan/claude-forge (2 stars, last pushed 4mo ago), licensed Unlicense. It adds 87 tokens to every session and 630 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 2026-08-31.

Analytics and metricsData and AI
Related

Other skills, from other repositories

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens