Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/DorianSchlede/nexus-templatenpx agentmods add skills/dorianschlede/nexus-template/langfuse-helpWrote 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/dorianschlede/nexus-template/langfuse-help)<a href="https://agentmods.dev/skills/dorianschlede/nexus-template/langfuse-help"><img src="https://agentmods.dev/badge/skills/dorianschlede/nexus-template/langfuse-help/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/dorianschlede/nexus-template/langfuse-help"><img src="https://agentmods.dev/badge/skills/dorianschlede/nexus-template/langfuse-help.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 | $0.00033 | $0.01264 |
| Opus 5 | $0.00016 | $0.00632 |
| Sonnet 5 | $0.00007 | $0.00253 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade A, and why
langfuse-help 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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Langfuse Help
Quick reference for Langfuse operations. For detailed patterns, see full reference:
cat 00-system/skills/meta/langfuse-help/SKILL.md
Available Skills (70+ operations)
Core Operations
| Skill | Description |
|---|---|
| langfuse-list-traces | List recent traces |
| langfuse-get-trace | Get trace WITH observations |
| langfuse-list-sessions | List sessions |
| langfuse-get-session | Get session (NO observations) |
| langfuse-list-observations | List spans/generations |
Scores
| Skill | Description |
|---|---|
| langfuse-list-scores | List evaluation scores |
| langfuse-create-score | Create score (with validation) |
| langfuse-delete-score | Delete score |
| langfuse-list-score-configs | List score configs |
Datasets & Prompts
| Skill | Description |
|---|---|
| langfuse-list-datasets | List datasets |
| langfuse-create-dataset-item | Add ground truth item |
| langfuse-list-prompts | List prompts |
Critical Patterns
Observations Require Individual Fetch
# GET /sessions/{id} does NOT include observations
# Must call GET /traces/{id} for each trace
for trace in session["traces"]:
full = client.get(f"/traces/{trace['id']}")
obs = full.get("observations", [])
CATEGORICAL Scores Use String Value
# CORRECT
{"value": "complete", "configId": "..."}
# WRONG (400 error)
{"value": 2, "stringValue": "complete"}
Use create_score.py for Validation
# Validates before sending (API accepts garbage!)
uv run python create_score.py --trace {id} --name goal_achievement \
--string-value complete --config-id {uuid}
# List all known configs
uv run python create_score.py --list-configs
# With metadata (rich JSON, ~1MB limit)
uv run python create_score.py --trace {id} --name session_notes --value 1 \
--metadata '{"trace_ids": ["a","b"], "findings": [...]}'
Score Config IDs
CONFIG_IDS = {
# Quality Dimensions (NUMERIC 0-1 unless noted)
"goal_achievement": "68cfd90c-8c9e-4907-808d-869ccd9a4c07", # CATEGORICAL
"tool_efficiency": "84965473-0f54-4248-999e-7b8627fc9c29",
"process_adherence": "651fc213-4750-4d4e-8155-270235c7cad8",
"context_efficiency": "ae22abed-bd4a-4926-af74-8d71edb1925d",
"error_handling": "96c290b7-e3a6-4caa-bace-93cf55f70f1c", # CATEGORICAL
"output_quality": "d33b1fbf-d3c6-458c-90ca-0b515fe09aed",
"overall_quality": "793f09d9-0053-4310-ad32-00dc06c69a71",
# Meta Scores
"root_cause_issues": "669bead7-1936-4fc4-bae8-e7814c9eab04", # CATEGORICAL
"session_improvements": "2e87193b-c853-4955-b2f0-9fa572531681", # CATEGORICAL
"session_notes": "67640329-0c03-4be6-bc9f-49765a0462b5", # NUMERIC (value=1 + comment/metadata)
}
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.
- 8d ago First seen · 141 lines · 33 tokens per session scan A d2b515414be7
langfuse-help is a skill published in the GitHub repository DorianSchlede/nexus-template (8 stars, last pushed 7mo ago), licensed MIT. It adds 33 tokens to every session and 1,264 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…