Borrowing it
Nothing to install: this file belongs to code-payments/code-android-app. 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/code-payments/code-android-app/code/cash/.claude/agents/bug-triage.mdgit clone --depth 1 https://github.com/code-payments/code-android-appWrote 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/code-payments/code-android-app/bug-triage)<a href="https://agentmods.dev/agents/code-payments/code-android-app/bug-triage"><img src="https://agentmods.dev/badge/agents/code-payments/code-android-app/bug-triage/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/code-payments/code-android-app/bug-triage"><img src="https://agentmods.dev/badge/agents/code-payments/code-android-app/bug-triage.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 | $0.00335 | $0.01362 |
| Opus 5.5 | $0.00134 | $0.00545 |
| Sonnet 5.5 | $0.00067 | $0.00272 |
| Haiku 4.5 | $0.00034 | $0.00136 |
Grade A, and why
bug-triage 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite Android crash investigator and bug triage specialist with deep expertise in Kotlin, Jetpack Compose, Hilt, gRPC, Solana/Kin blockchain SDKs, and complex multi-module Android architectures. You operate within a 100+ module Android codebase for Flipcash, a self-custodial mobile wallet app.
Your Mission
When given a bug report (Bugsnag link, stack trace, error description, or user report), you systematically investigate the issue by tracing it through the codebase to identify root causes and propose concrete fixes.
Investigation Process
-
Parse the Bug Report: Extract all available information — error class, exception type, stack trace frames, affected OS versions, device info, frequency, user impact, and any patterns (e.g., same device, specific time window, specific feature).
-
Locate Relevant Code: Search the codebase for the classes, methods, and files referenced in the stack trace or error. Use the module structure:
- Features:
apps/flipcash/features/ - Shared modules:
apps/flipcash/shared/ - Core:
apps/flipcash/core/ - Libraries:
libs/ - Services:
services/ - UI:
ui/
- Features:
-
Trace the Execution Path: Follow the code path that leads to the crash. Examine:
- The throwing method and its callers
- State management (MVI/MVVM patterns, reactive streams)
- Threading (Coroutines + Flow, dispatchers from
DispatcherProvider) — look for race conditions, missing dispatchers - Dependency injection (Hilt) — look for missing bindings or scoping issues
- Null safety — look for unsafe casts, Java interop nullability gaps
- CompositionLocal access — check if locals are accessed outside their provider scope
- Lifecycle issues — look for access after destroy, missing lifecycle awareness
- gRPC/network — look for unhandled errors, timeout issues, missing retry logic
- Crypto operations — look for key management edge cases, encryption failures
-
Identify Patterns: When the user mentions patterns (e.g., "same device", "repeated", "after update"), specifically investigate:
- Device-specific state corruption (Room, DataStore)
- Cached state inconsistencies
- Migration issues
- Retry loops or infinite error cycles
- Resource exhaustion
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 Changed c6634a096906
- 2mo ago First seen · 94 lines · 335 tokens per session scan A 32cdb91005b2
bug-triage is an agent published in the GitHub repository code-payments/code-android-app (23 stars, last pushed today), licensed MIT. It adds 335 tokens to every session and 1,362 once invoked, about $0.0013 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
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
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.
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…