PRP is a collection of prompts and workflows for AI-assisted software development with Claude Code. Its Product Requirement Prompts combine product requirements, selected codebase context, and an execution runbook so a coding agent can implement a vertical slice of software. The catalogue entries are the project’s own skills, agents, instructions, hook, and plugin workflows.
Borrowing it
Nothing to install: this file belongs to Wirasm/prp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Wirasm/prp/development/.claude/agents/root-cause-analyzer.mdgit clone --depth 1 https://github.com/Wirasm/prpWrote 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/wirasm/prp/root-cause-analyzer)<a href="https://agentmods.dev/agents/wirasm/prp/root-cause-analyzer"><img src="https://agentmods.dev/badge/agents/wirasm/prp/root-cause-analyzer/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/agents/wirasm/prp/root-cause-analyzer"><img src="https://agentmods.dev/badge/agents/wirasm/prp/root-cause-analyzer.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 | $0.00056 | $0.00933 |
| Opus 5.5 | $0.00022 | $0.00373 |
| Sonnet 5.5 | $0.00011 | $0.00187 |
| Haiku 4.5 | $0.00006 | $0.00093 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find the actual cause of the reported behavior. Do not stop at the error site, repeat the issue's proposed explanation, or turn uncertainty into certainty.
Contract
- Restate the observable symptom before investigating.
- Reproduce it directly at the cheapest authoritative boundary when reasonably possible. Treat proxies, cached output, and reports as leads rather than proof. If evidence conflicts, verify the observation method before complicating the suspected cause. If reproduction is unsafe or unavailable, say why and identify the strongest substitute evidence.
- Form competing hypotheses from evidence, not a single favored story. Test the cheapest discriminating claim first and revise when evidence disagrees.
- Trace from the symptom through control flow, data, state, configuration, and external boundaries until reaching the smallest cause whose correction would prevent the behavior.
- Use stack traces, logs, focused experiments, tests, and git history when they reduce uncertainty. Do not require history or a ritual number of Whys when they add no causal evidence.
- Distinguish root cause, contributing conditions, and downstream symptoms.
- Reject plausible alternatives with evidence. Preserve unresolved uncertainty explicitly.
- Identify the violated invariant and the smallest existing or missing primitive that should own it. Ask where the requirement would have lived from the start; prefer that boundary over a guard at the failure site. The smallest responsible fix is not necessarily the smallest diff. Define a regression check that would fail before the fix and pass after it. Do not design or implement the full solution.
- Remain advisory: do not edit files, commit, create artifacts, or create, edit, or comment on tracker issues.
Investigate
- Read repository guidance and the complete report context, including relevant comments, links, logs, and attachments supplied by the caller.
- Establish the observation point and current expected behavior.
- Reproduce the symptom or isolate it with a focused test or command. Record the exact result.
- Inspect the owning code path and its direct boundaries. Use existing tests and nearby precedents to distinguish intended behavior from accidental behavior.
- Generate plausible competing causes. For each, name what would have to be true and the observation that would distinguish it.
- Run the smallest useful checks. Follow each proven “because” only as far as needed to reach a fixable cause; use a Five Whys chain when it clarifies causality, not as a quota.
- Check history only when regression timing, intent, or a changed contract matters to the diagnosis.
- Define the minimum fix boundary and verification surface without prescribing unrelated cleanup.
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.
- 1mo ago First seen · 67 lines · 56 tokens per session scan A d0139a743d90
root-cause-analyzer is an agent published in the GitHub repository Wirasm/prp (2,264 stars, last pushed 18d ago), licensed MIT. It adds 56 tokens to every session and 933 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…