ariffazil/arifos/langfuse-arifos
Claude Code and agent skill by ariffazil/arifos
- community
Checking that the SKILL.md file is still in the repository.
Instrument arifOS constitutional AI kernel with Langfuse LLM tracing. Use when (1) adding Langfuse tracing to arifOS tool calls, (2) wiring arifOS telemetry to Langfuse cloud or self-hosted, (3) querying arifOS trace data from Langfuse, (4) migrating arifOS mind_reason/heart_critique calls to Langfuse spans. DITEMPA BUKAN DIBERI — Forged, Not Given.
Install
npx vskill@latest install ariffazil/arifos/langfuse-arifosSKILL.md
arifOS-Langfuse Skill
Instrument arifOS constitutional AI operations with Langfuse LLM tracing.
Architecture
arifOS uses Langfuse Python SDK v3 with context manager pattern — spans auto-close on exit.
Credentials
arifOS → Langfuse (cloud Japan):
arifOS → Langfuse (self-hosted on VPS):
Key Patterns
Correct span creation (v3 context manager)
Tool call tracing in arifOS
In arifosmcp/runtime/telemetry.py, record_tool_call() method:
After flush() the span appears in Langfuse dashboard under the project.
Environment setup in arifOS container
arifOS Tracing Scope
| Tool | Traced | Priority | |
|---|---|---|---|
| arif_judge_deliberate | ✅ active | P0 | |
| arif_mind_reason | ⚠️ pilot | P1 | |
| arif_heart_critique | ⚠️ pilot | P1 | |
| arif_session_init | 🔜 next | P2 | |
| Others | ❌ not wired | — |
Workflows
1. Verify arifOS Langfuse wiring
2. Wire a new tool to Langfuse
- Find the tool handler in
arifosmcp/runtime/tools.py - Add
trace_tool_call()from telemetry after successful execution - Instrument input_hash / output_hash (redacted) + metadata dict
- Test: send live call, check Langfuse dashboard
3. Inspect traces via API
4. Add scoring to traces
Troubleshooting
| Symptom | Fix | |
|---|---|---|
ModuleNotFoundError: No module named 'langfuse' | pip install langfuse in container | |
AttributeError: 'Langfuse' object has no attribute 'trace' | Use v3 context manager pattern, not .trace() | |
Context error: No active span | Wrap with with lf.start_as_current_observation() as span: | |
401 Unauthorized | Check API keys are correct + LANGFUSE_HOST matches region | |
| Traces not appearing after flush | Check LANGFUSE_HOST network access from container | |
langfuse-web returns 404 | Self-hosted needs /api/public/ path prefix |
Documentation
- Langfuse Docs: https://langfuse.com/docs
- arifOS Observatory (public): https://arifos.arif-fazil.com/observatory/
- arifOS Langfuse tracing status: Langfuse cloud (jp region) — partial, pilot stage
References
- Full Langfuse instrumentation guide: https://langfuse.com/docs/observability/sdk/instrumentation
- Python SDK v3: https://langfuse.com/docs/sdk/python/sdk-v3
- CLI: https://langfuse.com/docs/api-and-data-platform/features/agent-skill
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/langfuse-arifos/SKILL.md
Popularity
- Repository stars
- 51
- Repository forks
- 9
- 7-day trend score
- 20
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/ariffazil/arifos/langfuse-arifos)