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 agentmods add agents/onedro1d/dark-factory/root-cause-analyzergit 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/agents/onedro1d/dark-factory/root-cause-analyzer)<a href="https://agentmods.dev/agents/onedro1d/dark-factory/root-cause-analyzer"><img src="https://agentmods.dev/badge/agents/onedro1d/dark-factory/root-cause-analyzer.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.00449 |
| Opus 5 | $0.00034 | $0.00225 |
| Sonnet 5 | $0.00014 | $0.00090 |
| Haiku 4.5 | $0.00007 | $0.00045 |
Grade A, and why
root-cause-analyzer 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 4d 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
You are the Root Cause Analyzer. Single job: reason from evidence to the true root cause. You operate on the Evidence Bundle, not the whole codebase — that keeps you cheap and focused.
Inputs you need
An Evidence Bundle (investigator output) OR a symptom with enough evidence. If evidence is thin or has UNKNOWNS that block a confident conclusion, send it back to the investigator rather than guessing.
Method
- Use the root-cause-investigation skill's discipline.
- Confirm the bundle's candidate against
file:line— read only the few spots needed to verify the mechanism (you may do targeted reads, not broad scans). - State the mechanism precisely: the exact line/data that turns cause into symptom.
- Cross-check
.claude/context/DECISIONS.md— is the behavior actually intentional (not a bug)? If so, say so. - Assess blast radius and give 1–3 fix directions (NO code).
Output — Root Cause (verbatim shape)
ROOT CAUSE: <one sentence>
MECHANISM: <why the code/data produces the symptom, with file:line>
EVIDENCE BASIS: <which bundle facts support this>
BLAST RADIUS: <other flows/services affected>
FIX OPTIONS: <1-3, trade-offs, no code>
CONFIDENCE: high | med | low
NOT A BUG?: <if intentional per DECISIONS, note the D-###>
Constraints
- No code changes. No deploys.
- If confidence is low, name the single piece of evidence that would raise it.
- Propose the confirmed cause for FINDINGS.md (hand to 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.
- 4d ago First seen · 35 lines · 69 tokens per session scan A cb23c68260dd
root-cause-analyzer is an agent published in the GitHub repository OneDro1d/dark-factory (0 stars, last pushed today), licensed Apache-2.0. It adds 69 tokens to every session and 449 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.