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 OneDro1d/dark-factory --skill root-cause-investigationgit clone --depth 1 https://github.com/OneDro1d/dark-factoryWrote 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/onedro1d/dark-factory/root-cause-investigation)<a href="https://agentmods.dev/skills/onedro1d/dark-factory/root-cause-investigation"><img src="https://agentmods.dev/badge/skills/onedro1d/dark-factory/root-cause-investigation/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/onedro1d/dark-factory/root-cause-investigation"><img src="https://agentmods.dev/badge/skills/onedro1d/dark-factory/root-cause-investigation.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 | $0.00075 | $0.00501 |
| Opus 5 | $0.00037 | $0.00251 |
| Sonnet 5 | $0.00015 | $0.00100 |
| Haiku 4.5 | $0.00007 | $0.00050 |
Grade A, and why
root-cause-investigation 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 10d 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.
What it actually says
Root-Cause Investigation (evidence-first)
Goal: fast, correct root cause with minimum tokens. A plausible guess is worse than "need more evidence."
Procedure
- Check memory:
.claude/context/FINDINGS.md— if already root-caused, reuse it and stop. - Locate: use SERVICE-MAP + the relevant
<service>/CLAUDE.mdto find where the symptom lives. - Trace: follow the flow (dependency-mapping) to the component where expected ≠ actual.
- Gather evidence before concluding: the exact
file:line, the data/log/state that proves it, and what you ruled out. - Confirm the mechanism: state precisely why the code produces the symptom (e.g. "reads a scope column the copy path never writes → 0 rows").
- Escalate, don't guess: if you can't confirm in code/data, list the missing evidence and what would resolve it.
Common failure modes to check first
- Silent zero-records (record-element detection / stale build).
- Object-store key drift writer↔reader (consumer requeues forever).
- Stale container / non-regenerated artifact (silent).
- Secondary store write inside the primary DB txn → timeout under load.
- Restricted/non-restricted data misroute (fail-safe default).
- Poison vs transient Nack misclassification (dead-letter vs infinite requeue).
Output → Root Cause Analyzer / user
SYMPTOM: <observed>
ROOT CAUSE: <one sentence, mechanism>
EVIDENCE: <file:line, data/log, what was ruled out>
BLAST RADIUS: <other flows/services affected>
FIX OPTIONS: <1-3, no code> | CONFIDENCE: high/med/low
UNKNOWNS: <missing evidence, if any>
Confirmed causes get written to FINDINGS.md (via knowledge-keeper).
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.
- 10d ago First seen · 37 lines · 75 tokens per session scan A 63f6ac7fd67b
root-cause-investigation is a skill published in the GitHub repository OneDro1d/dark-factory (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 75 tokens to every session and 501 once invoked, about $0.0004 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 2026-09-01.
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.