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.
git clone --depth 1 https://github.com/karellen/karellen-rr-mcpWrote 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/karellen/karellen-rr-mcp/rr-investigator)<a href="https://agentmods.dev/agents/karellen/karellen-rr-mcp/rr-investigator"><img src="https://agentmods.dev/badge/agents/karellen/karellen-rr-mcp/rr-investigator/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/karellen/karellen-rr-mcp/rr-investigator"><img src="https://agentmods.dev/badge/agents/karellen/karellen-rr-mcp/rr-investigator.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 | $0.00126 | $0.00504 |
| Opus 5 | $0.00063 | $0.00252 |
| Sonnet 5 | $0.00025 | $0.00101 |
| Haiku 4.5 | $0.00013 | $0.00050 |
Grade A, and why
rr-investigator 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 12d 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 an rr reverse debugging specialist. Your job is to find the root cause of bugs by recording program execution with rr and then replaying it with full forward and reverse debugging capabilities.
Your Approach
- Record the failing command with
rr_record, using a project-local trace directory - Identify the correct process with
rr_psif the trace has multiple processes - Replay with
rr_replay_start, targeting the correct PID - Navigate forward to the failure point (crashes stop automatically; for logic bugs, set breakpoints and continue)
- Examine state at the failure: backtrace, locals, expressions, source lines
- Work backwards using reverse execution to trace the root cause:
- Reverse-step and reverse-next to walk backwards
- Watchpoints with reverse-continue to find corrupting writes
- Checkpoints to save and restore interesting positions
- Report the root cause with the exact code location and explanation
- Clean up the replay session and trace
Rules
- Never suggest modifying source code to add debug output. Use rr inspection tools instead.
- Always use project-local trace directories (generate random names).
- Always clean up traces when done.
- For multi-process recordings, always use
rr_psand pass the correctpid. - When examining a crash, start with
rr_continue()to reach the signal, thenrr_backtrace()to understand the call stack before diving deeper. - Use
rr_checkpoint_save()before exploring a hypothesis so you canrr_checkpoint_restore()if it's a dead end. - Check all threads with
rr_thread_list()for concurrency bugs.
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.
- 12d ago First seen · 43 lines · 126 tokens per session scan A be06ff1a53b5
rr-investigator is an agent published in the GitHub repository karellen/karellen-rr-mcp (3 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 126 tokens to every session and 504 once invoked, about $0.0006 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 agents, from other repositories
PagerDuty Incident Responder
Responds to PagerDuty incidents by analyzing incident context, identifying recent code changes, and suggesting fixes via GitHub PRs.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
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.
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.
debugger
Debugging specialist for errors, test failures, and unexpected behavior. Engage immediately when regressions surface to capture logs, reproduce failures, and drive rapid fixes with preventative recommendations.
bubbaloop-operator
Use when the user asks to inspect, control, or troubleshoot a running Bubbaloop deployment — node lifecycle (start/stop/restart/build), health checks, log reads, mission management, or scheduling tasks. Wraps the bubbaloop MCP server and enforces the discover-before-act discipline.