langfuse-coding-trace

langfuse-coding-trace is a skill for Codex from hashgraph-online/awesome-codex-plugins. It costs 118 tokens per session (1,362 once invoked), scanned A, original, Apache-2.0.

A tracing integration that records the major steps of a coding workflow in Langfuse, a self-hosted system for viewing application traces and timing. It reports events such as code generation, compilation, startup, testing, and fixes.

In plain words
What is it for?
Use it to record traces and spans for coding tasks, inspect step results and errors, and monitor workflows in a self-hosted Langfuse instance.
Why use it?
It makes a coding run's progress and failures visible after the fact without blocking the main workflow. Missing Langfuse credentials cause tracing to be skipped.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to record traces and spans for coding tasks, inspect step results and errors, and monitor workflows in a self-hosted Langfuse instance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hashgraph-online/awesome-codex-plugins/langfuse-coding-trace
Install

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.

Any agent
npx skills add hashgraph-online/awesome-codex-plugins --skill langfuse-coding-trace
Clone the repo
git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins

Made for: Codex.

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 langfuse-coding-trace

README.md
[![agentmods](https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/langfuse-coding-trace/github.svg)](https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/langfuse-coding-trace)
Your own site
<a href="https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/langfuse-coding-trace"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/langfuse-coding-trace/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 langfuse-coding-trace

Your own site · 80×15
<a href="https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/langfuse-coding-trace"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/langfuse-coding-trace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,362 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00118 $0.01362
Opus 5 $0.00059 $0.00681
Sonnet 5 $0.00024 $0.00272
Haiku 4.5 $0.00012 $0.00136

Measured 3d ago against content hash 10360269d0e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

langfuse-coding-trace 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (trace.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/Colin4k1024/tsp/skills/langfuse-coding-trace/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Langfuse 编码流程追踪

为编码工作流每个关键步骤异步上报 Trace/Span 到 Langfuse,不阻塞主流程。

前置条件

需设置以下环境变量(未设置时静默跳过追踪):

LANGFUSE_PUBLIC_KEY   # Langfuse 公钥
LANGFUSE_SECRET_KEY   # Langfuse 私钥
LANGFUSE_HOST         # 自部署地址,如 http://192.168.1.100:3000

脚本位置

<skills_dir>/langfuse-coding-trace/scripts/trace.py

调用前先确认 LANGFUSE_PUBLIC_KEY 是否存在,不存在则跳过所有追踪调用。


追踪点规范

第一步:开始编码会话 → 创建 Trace(同步,获取 trace_id)

TRACE_ID=$(python "<skills_dir>/langfuse-coding-trace/scripts/trace.py" trace-start \
  --name "logic-layer-method-impl" \
  --input '{"method": "目标方法名", "mode": "首次编码/需求变更"}')
echo "Trace started: $TRACE_ID"

中间步骤:每个大步骤 → 创建 Span(异步,后台执行)

# 开始 Span(同步获取 span_id,耗时极短)
SPAN_ID=$(python "<skills_dir>/langfuse-coding-trace/scripts/trace.py" span-start \
  --trace-id "$TRACE_ID" \
  --name "maven-qa")

# 执行实际步骤 ...(编译/运行/测试等)

# 结束 Span(异步,后台执行)
python "<skills_dir>/langfuse-coding-trace/scripts/trace.py" span-end \
  --span-id "$SPAN_ID" \
  --output '{"exit_code": 0, "result": "通过"}' \
  --level DEFAULT &

# 若失败,用 ERROR 级别
python "<skills_dir>/langfuse-coding-trace/scripts/trace.py" span-end \
  --span-id "$SPAN_ID" \
  --output '{"error": "错误摘要"}' \
  --level ERROR &

最后一步:结束 Trace(异步)

python "<skills_dir>/langfuse-coding-trace/scripts/trace.py" trace-end \
  --trace-id "$TRACE_ID" \
  --output '{"status": "success", "loops": 1, "compile": "pass", "run": "pass", "test": "95%"}' &

标准追踪点列表

步骤 Span 名称 input 字段 output 字段 失败 level
识别编码模式 identify-mode {} {"mode": "首次/变更"} WARNING
代码生成 code-generation {"files": [...]} {"files_modified": N} ERROR
QA 质量闸口 maven-qa {} {"compile": "pass", "pass_rate": "XX%", "criticalIssues": 0, "run": "pass"} ERROR
代码修复 code-fix {"error": "..."} {"files_fixed": [...]} WARNING

完整调用示例(配合 logic-layer-method-impl)

# 检查环境变量
if [ -z "$LANGFUSE_PUBLIC_KEY" ]; then
  echo "Langfuse 未配置,跳过追踪"
  LANGFUSE_ENABLED=false
else
  LANGFUSE_ENABLED=true
fi

SCRIPT="<skills_dir>/langfuse-coding-trace/scripts/trace.py"

# 1. 开始 Trace
[ "$LANGFUSE_ENABLED" = true ] && \
  TRACE_ID=$(python "$SCRIPT" trace-start --name "logic-layer-method-impl" --input '{"method":"xxx"}')

# 2. 识别模式 Span
[ "$LANGFUSE_ENABLED" = true ] && \
  SPAN_MODE=$(python "$SCRIPT" span-start --trace-id "$TRACE_ID" --name "identify-mode")
# ... 执行识别逻辑 ...
[ "$LANGFUSE_ENABLED" = true ] && \
  python "$SCRIPT" span-end --span-id "$SPAN_MODE" --output '{"mode":"首次编码"}' &

# 3. 代码生成 Span(同上模式)

# 4. QA 验证 Span(编译 + 单测 + 静态分析)
[ "$LANGFUSE_ENABLED" = true ] && \
  SPAN_QA=$(python "$SCRIPT" span-start --trace-id "$TRACE_ID" --name "maven-qa")
# ... 调用 maven-qa skill ...
[ "$LANGFUSE_ENABLED" = true ] && \
  python "$SCRIPT" span-end --span-id "$SPAN_QA" --output '{"compile":"pass","pass_rate":"98%","criticalIssues":0,"run":"pass"}' &

# 5. 结束 Trace
[ "$LANGFUSE_ENABLED" = true ] && \
  python "$SCRIPT" trace-end --trace-id "$TRACE_ID" --output '{"status":"success"}' &

Read the full file on GitHub · 130 lines

Files

What ships with it

2 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.

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. 3d ago First seen · 130 lines · 118 tokens per session scan A 10360269d0e5

Subscribe to this mod's changes

langfuse-coding-trace is a skill published in the GitHub repository hashgraph-online/awesome-codex-plugins (956 stars, last pushed today), licensed Apache-2.0. It adds 118 tokens to every session and 1,362 once invoked, about $0.0006 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 2026-09-05.

Related

Other skills, from other repositories

search

Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.

taishi-i/awesome-ChatGPT-repositories · 57 tokens

sprr

Single PR reviewer for awesome-quant. Use when the user asks to review, validate, comment on, label, close, or merge one specific pull request that adds README.md entries. Triggers include "sprr", "review PR", "check PR", and "validate contribution".

wilsonfreitas/awesome-quant · 60 tokens

bprr

Bulk PR reviewer for awesome-quant. Use when the user asks to review all open PRs, review unreviewed PRs, bulk review, or mentions "bprr". Reviews open PRs lacking the reviewed label and presents a summary before any merge/comment/label action.

wilsonfreitas/awesome-quant · 61 tokens

drawio-reconstruction

Reconstructs reference images into high-fidelity, editable Draw.io files with rendered previews: native Draw.io elements carry text and structure, SVG covers simple icons that match the reference, and cropped or transparent PNGs preserve complex visuals. Use when the user wants a diagram image, research figure…

HKUSTDial/Supervisor-Skills · 102 tokens

benchmark-paper-template

Structures Benchmark and Evaluation papers using the five-pillar framework (Research Gap, Construction Pipeline, Evaluation Framework, Empirical Findings, optional Companion Method). Returns a completeness audit, a six-part Introduction logic chain, a Section 2-7 skeleton, and a pre-submission checklist. Use when…

HKUSTDial/Supervisor-Skills · 96 tokens

reverse-engineering-android-malware-with-jadx

Reverse engineers malicious Android APK files using JADX decompiler to analyze Java/Kotlin source code, identify malicious functionality including data theft, C2 communication, privilege escalation, and overlay attacks. Examines manifest permissions, receivers, services, and native libraries. Activates for requests…

adriannoes/awesome-agentic-ai · 82 tokens