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 SHGrowth/om-superpowers --skill om-troubleshootergit clone --depth 1 https://github.com/SHGrowth/om-superpowersWrote 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/shgrowth/om-superpowers/om-troubleshooter)<a href="https://agentmods.dev/skills/shgrowth/om-superpowers/om-troubleshooter"><img src="https://agentmods.dev/badge/skills/shgrowth/om-superpowers/om-troubleshooter/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/shgrowth/om-superpowers/om-troubleshooter"><img src="https://agentmods.dev/badge/skills/shgrowth/om-superpowers/om-troubleshooter.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 | $0.00098 | $0.04406 |
| Opus 5 | $0.00049 | $0.02203 |
| Sonnet 5 | $0.00020 | $0.00881 |
| Haiku 4.5 | $0.00010 | $0.00441 |
Grade A, and why
om-troubleshooter 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 11d 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.
3. **Does the API return data?** Test with `curl` or browser devtools How it starts
The opening of the file, as written. The whole thing — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Troubleshooter
Diagnose and fix common issues in Open Mercato standalone apps. Follow the systematic approach: identify symptoms, check common causes, verify fixes.
STOP — Upstream bug routing (read first)
Before reading anything else in this skill, check whether the symptom points at OM core. If yes, route to om-cto/references/upstream-bug-triage.md and do NOT propose a downstream fix or "draft an upstream PR" inline.
Trigger conditions — any of these means STOP and route:
- A stack trace, error log, or breakpoint lands inside
node_modules/@open-mercato/*(or a checked-out@open-mercato/*package). - You found yourself reading source from
node_modules/@open-mercato/*to diagnose. If the diagnostic path went through OM core code, the bug class is "upstream until proven otherwise." - A core function returns wrong data, a contract doesn't match its types/JSDoc, or a widget injection / enricher / interceptor / event subscriber doesn't fire when the wiring looks correct.
- You're about to suggest changes inside
node_modules/@open-mercato/*— even mentally framed as "would need to". - You're about to offer the user a choice that includes "draft an upstream PR" or "patch upstream".
What "route" means concretely:
- Stop the diagnosis hand-off. Do NOT enumerate fix options to the user yet.
- Invoke
om-ctoand loadreferences/upstream-bug-triage.md. Provide the six required inputs (symptom / source location / expected vs actual / repro / proposed workaround sketch / calling agent + task). - Follow the verdict om-cto returns. If the verdict is
confirmed-new-bug, the upstream patch handoff is aWriteto<om_core_path>/agents/tasks/<YYYY-MM-DD>-<slug>/README.md— NOT a PR opened from the consumer-app session, and NOT an entry appended to<om_core_path>/ISSUE_LOG.md. The drain agent picks up by directory listing, not by log scanning.
Why this exists: in past sessions, the troubleshooter found upstream bugs (e.g., raiseCrudError not handling nested error.message in @open-mercato/ui), offered "draft an upstream PR" as a third option alongside local fixes, and on user redirect appended to ISSUE_LOG.md instead of using agents/tasks/<DATE>-<slug>/README.md. Both bypassed the triage protocol. This block is here so it doesn't happen again.
What ships with it
1 file 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.
- 11d ago First seen · 464 lines · 98 tokens per session scan A 833fd7b4a656
om-troubleshooter is a skill published in the GitHub repository SHGrowth/om-superpowers (6 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 4,406 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.