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 commands/tommymorgan/claude-plugins/root-causegit clone --depth 1 https://github.com/tommymorgan/claude-pluginsWhat 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 | $0.00019 | $0.00271 |
| Opus 5 | $0.00010 | $0.00135 |
| Sonnet 5 | $0.00004 | $0.00054 |
| Haiku 4.5 | $0.00002 | $0.00027 |
Grade A, and why
tommymorgan:root-cause 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 2d 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
Perform systematic root cause analysis on the reported problem using the root-cause-analyzer agent.
Problem Context: $ARGUMENTS
Instructions:
- Launch the root-cause-analyzer agent to investigate this problem
- The agent will autonomously perform five whys analysis without user prompts
- Each investigation level will be shown progressively as the agent works
- The agent will continue until identifying an actionable root cause
- After root cause is identified, proceed to implementing the fix
Agent Behavior:
- Gathers evidence from code, logs, and outputs
- Asks "why?" iteratively based on concrete findings
- Shows structured output for each investigation level
- Determines when root cause criteria are met (actionable, explanatory, terminal)
- Completes automatically when root cause is found
Your Role:
- Use the Task tool to launch the root-cause-analyzer agent
- Provide the problem context to the agent
- Wait for agent to complete root cause analysis
- Once agent identifies root cause, proceed with the recommended fix approach
Do not attempt speculative fixes before root cause is identified.
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.
- 2d ago First seen · 34 lines · 19 tokens per session scan A 715797432be7
tommymorgan:root-cause is a command published in the GitHub repository tommymorgan/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 271 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.