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 makifbaysal/tasktrooper --skill root-cause-debugginggit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/root-cause-debugging)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/root-cause-debugging"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/root-cause-debugging/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/makifbaysal/tasktrooper/root-cause-debugging"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/root-cause-debugging.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 | $0.00047 | $0.01500 |
| Opus 5.5 | $0.00019 | $0.00600 |
| Sonnet 5.5 | $0.00009 | $0.00300 |
| Haiku 4.5 | $0.00005 | $0.00150 |
Grade A, and why
root-cause-debugging scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
This is the skill: before anything else, name ONE command you have already run that goes red on THIS symptom — a failing test, a `curl` against the running service, a `browser_read_dom` that doesn't find what it should, How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Root-Cause Debugging
Overview
Random fixes waste time and create new bugs. Quick patches mask underlying issues.
Core principle: ALWAYS find the root cause before attempting fixes. Symptom fixes are failure.
The Iron Law
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
Use this for ANY technical issue: a task returned to need_revision, a failing test, a red pipeline, unexpected behavior. Use it ESPECIALLY under time pressure — systematic is faster than guess-and-check thrashing.
The Four Phases
Complete each phase before the next.
Phase 1 — Build a feedback loop, then investigate
This is the skill: before anything else, name ONE command you have already run that goes red on THIS symptom — a failing test, a curl against the running service, a browser_read_dom that doesn't find what it should, a replayed payload. No loop, no hypothesis. If none exists, write the smallest one that reproduces it (a test is the default; a curl/DOM read is the fallback when the bug is only visible live) before reading another line of code.
- Read the feedback completely: the reviewer/QA/pipeline comment on the task, the full error output, stack traces, exact files/lines/messages. They often contain the exact answer.
- Reproduce consistently in the task workspace with the loop from above: does it happen every time? Not reproducible → gather more data, don't guess.
- Check recent changes: git diff, recent commits on the task branch, config changes.
- Stage/prod symptom (a runtime error, not a local failure): before reading code,
get_environmentfor the environment,list_runtime_errorswithnew: trueto see whether the group started with the latest deploy, thenquery_runtime_logswithtext:set to the error message. You hold these tools; use them before guessing from the code alone. - Multi-component systems (API → service → database): add diagnostic logging at each component boundary — what enters, what exits — run once, and locate WHICH layer breaks before touching anything. Tag every line you add with a unique marker, e.g.
[DEBUG-a4f2], so cleanup is onegrep_codefor the tag before you finish — an untagged debug log left behind is a review finding. - Trace the bad value backward from where the error appears to where it originates. Fix at the source, not at the symptom.
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 · 99 lines · 47 tokens per session scan A 40ee33157312
root-cause-debugging is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 1,500 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-05.
Other skills, from other repositories
doca-flow
Build and debug DOCA Flow applications on supported NVIDIA NICs/DPUs: define match/action pipes, initialize ports and representors, choose forwarding targets, validate pipes before hardware programming, read counters, match the Flow version to the installed DOCA release, and diagnose Flow API errors. Trigger on DOCA…
dynamo-interconnect-check
Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deployment up (especially disagg/multi-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.
mcore-create-issue
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
jetson-print-bsp-info
Use when you need to print Jetson BSP info (L4T version, board configs, rootfs state) from a LinuxforTegra root on the host PC. This is an example skill.
doca-dpa-hl-tracer
Use this skill when the user runs docadpahltracer to capture/decode DPA-side traces at the programming-events layer (kernel entry/exit, sync points, comm primitive calls, RDMA WR submission, completion drain) — picking TRACE vs CRIT, tuning the JSON config (file-size limits + filesizelimitpolicy, thread…
doca-debug
Use this skill when the user is debugging any DOCA symptom — a build that won't compile, a link step that can't resolve a doca symbol, a runtime call returning DOCAERROR, a silent service or tool, or a stack trace / valgrind / core dump — and needs the layered ladder (install → version → build → link → runtime →…