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 bobmatnyc/claude-mpm-skills --skill root-cause-tracinggit clone --depth 1 https://github.com/bobmatnyc/claude-mpm-skillsWrote 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/bobmatnyc/claude-mpm-skills/root-cause-tracing)<a href="https://agentmods.dev/skills/bobmatnyc/claude-mpm-skills/root-cause-tracing"><img src="https://agentmods.dev/badge/skills/bobmatnyc/claude-mpm-skills/root-cause-tracing/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/bobmatnyc/claude-mpm-skills/root-cause-tracing"><img src="https://agentmods.dev/badge/skills/bobmatnyc/claude-mpm-skills/root-cause-tracing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00018 | $0.01342 |
| Opus 5 | $0.00009 | $0.00671 |
| Sonnet 5 | $0.00004 | $0.00268 |
| Haiku 4.5 | $0.00002 | $0.00134 |
Grade A, and why
root-cause-tracing 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 7d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Root Cause Tracing
Overview
Bugs often manifest deep in the call stack (git init in wrong directory, file created in wrong location, database opened with wrong path). Your instinct is to fix where the error appears, but that's treating a symptom.
Core principle: Trace backward through the call chain until you find the original trigger, then fix at the source.
This skill is a specialized technique within the systematic-debugging workflow, typically applied during Phase 1 (Root Cause Investigation) when dealing with deep call stacks.
When to Use This Skill
Use root-cause-tracing when:
- Error happens deep in execution (not at entry point)
- Stack trace shows long call chain
- Unclear where invalid data originated
- Need to find which test/code triggers the problem
- Symptom appears far from actual cause
Relationship with systematic-debugging:
- systematic-debugging: The overall framework (Phases 1-4)
- root-cause-tracing: A specific technique for Phase 1 investigation
- Use root-cause-tracing WITHIN systematic-debugging Phase 1
The Iron Law
NEVER FIX JUST WHERE THE ERROR APPEARS
ALWAYS TRACE BACK TO FIND THE ORIGINAL TRIGGER
Fixing symptoms creates bandaid solutions that mask root problems.
Core Principles
- Trace Backward: Follow call chain from symptom to source
- Find Original Trigger: Identify where bad data/state originated
- Fix at Source: Address root cause, not symptom
- Defense-in-Depth: Add validation at each layer after fixing source
Quick Start
The 5-Step Trace Process
- Observe the Symptom: What error message? What failed operation?
- Find Immediate Cause: What code directly causes this error?
- Ask What Called This: Trace one level up the call stack
- Keep Tracing Up: Continue until you find the original trigger
- Fix at Source + Defense: Fix root cause and add layer validation
Decision Tree
Error appears deep in stack?
→ Yes: Start tracing backward
→ Can identify caller? → Trace one level up → Repeat
→ Cannot identify caller? → Add instrumentation (see advanced-techniques.md)
→ No: May not need tracing (error at entry point)
What ships with it
5 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.
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.
- 7d ago First seen · 155 lines · 18 tokens per session scan A ffc34ef0f676
root-cause-tracing is a skill published in the GitHub repository bobmatnyc/claude-mpm-skills (74 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,342 once invoked, about $0.0001 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
Root Cause Tracing
Systematically trace bugs backward through call stack to find original trigger.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
phoenix-observability
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
trulens-instrumentation
Instrument LLM apps with TruLens OTEL-based tracing - from setup to debugging and optimization.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
trace
Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with a final-integration review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why…