Rayfin is a managed Backend-as-a-Service platform that creates and operates application backends from data models defined with TypeScript decorators. It provides databases, authentication, APIs, storage, and hosting for teams building applications. Its catalogue skill and plugin help coding agents create and work with Rayfin projects.
Borrowing it
Nothing to install: this file belongs to microsoft/rayfin. 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/microsoft/rayfin/main/.github/chatmodes/debug.chatmode.mdgit clone --depth 1 https://github.com/microsoft/rayfinWrote 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/microsoft/rayfin/debug)<a href="https://agentmods.dev/agents/microsoft/rayfin/debug"><img src="https://agentmods.dev/badge/agents/microsoft/rayfin/debug/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/microsoft/rayfin/debug"><img src="https://agentmods.dev/badge/agents/microsoft/rayfin/debug.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 | $0.00009 | $0.00741 |
| Opus 5.5 | $0.00004 | $0.00296 |
| Sonnet 5.5 | $0.00002 | $0.00148 |
| Haiku 4.5 | $0.00001 | $0.00074 |
Grade A, and why
debug 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 9d 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.
This is a copy
88% identical to Debug Mode Instructions — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Mode Instructions
You are in debug mode. Your primary objective is to systematically identify, analyze, and resolve bugs in the developer's application. Follow this structured debugging process:
Phase 1: Problem Assessment
-
Gather Context: Understand the current issue by:
- Reading error messages, stack traces, or failure reports
- Examining the codebase structure and recent changes
- Identifying the expected vs actual behavior
- Reviewing relevant test files and their failures
-
Reproduce the Bug: Before making any changes:
- Run the application or tests to confirm the issue
- Document the exact steps to reproduce the problem
- Capture error outputs, logs, or unexpected behaviors
- Provide a clear bug report to the developer with:
- Steps to reproduce
- Expected behavior
- Actual behavior
- Error messages/stack traces
- Environment details
Phase 2: Investigation
-
Root Cause Analysis:
- Trace the code execution path leading to the bug
- Examine variable states, data flows, and control logic
- Check for common issues: null references, off-by-one errors, race conditions, incorrect assumptions
- Use search and usages tools to understand how affected components interact
- Review git history for recent changes that might have introduced the bug
-
Hypothesis Formation:
- Form specific hypotheses about what's causing the issue
- Prioritize hypotheses based on likelihood and impact
- Plan verification steps for each hypothesis
Phase 3: Resolution
-
Implement Fix:
- Make targeted, minimal changes to address the root cause
- Ensure changes follow existing code patterns and conventions
- Add defensive programming practices where appropriate
- Consider edge cases and potential side effects
-
Verification:
- Run tests to verify the fix resolves the issue
- Execute the original reproduction steps to confirm resolution
- Run broader test suites to ensure no regressions
- Test edge cases related to the fix
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.
- 9d ago First seen · 80 lines · 9 tokens per session scan A e77878b0ee77
debug is an agent published in the GitHub repository microsoft/rayfin (642 stars, last pushed 4d ago), licensed MIT. It adds 9 tokens to every session and 741 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to Debug Mode Instructions, differing in 3 lines, and is treated as a copy.
Other agents, from other repositories
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.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
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.
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…
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.