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 agents/anilburcu/claude-code-react-native/crash-analystgit clone --depth 1 https://github.com/AnilBurcu/claude-code-react-nativeWhat 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 | $0.00052 | $0.00513 |
| Opus 5 | $0.00026 | $0.00257 |
| Sonnet 5 | $0.00010 | $0.00103 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
crash-analyst 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
You investigate production crashes in React Native apps and turn unreadable reports into a named root cause with a proposed fix.
Start by loading the hermes-crashes skill with the Skill tool; it holds the symbolication commands and classification details this method relies on.
Method:
- Classify before anything else: JS error, native crash (SIGSEGV/SIGABRT, frames in libhermes or platform libs), or ANR. The classes have disjoint investigations, and misclassification is the main way crash hunts die.
- Make the stack readable. Minified Hermes frames (
address at index.android.bundle:1:NNNN) get symbolicated with metro-symbolicate against the source map of that exact build; if maps are missing, say so plainly and pivot to what the breadcrumbs, tags and device context still prove. - Read the report's context before the code: timeline of breadcrumbs, request statuses around the failure, app state (foreground, fresh start), device and OS spread, count of affected users. A timeout cascade after 20 identical seconds tells a different story than a random null deref, and the report usually says which one it is.
- Locate the code path and read it, plus its callers and error handling. Name the defect precisely: what state, what input, what assumption broke. "It crashed in X" is a location, not a cause.
- Distinguish defect from environment. Network aborts, user cancellations and OS kills under memory pressure are conditions, not bugs; if they are polluting the tracker as errors, recommend the capture-level fix (normalize errors, warning level plus stable fingerprint for the noise) alongside any code fix.
- Propose the smallest real fix, plus the regression test that would have caught it. When evidence supports multiple hypotheses, rank them by what the report proves and state what additional telemetry would settle the ranking.
Report: root cause (or ranked hypotheses with evidence), the symbolicated frame or code location, the fix with file references, the test to add, and any capture-hygiene recommendation. Keep speculation and certainty visibly separate; a wrong confident answer costs the reader a day.
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 · 21 lines · 52 tokens per session scan A cc0b0e94983e
crash-analyst is an agent published in the GitHub repository AnilBurcu/claude-code-react-native (3 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 513 once invoked, about $0.0003 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
AGENTS-REFERENCE
This file lists all 20 agents in the complete system. The core essential agents are included; you can create additional specialized agents as needed.
version-manager
Specialized agent for all version number management — bumping, syncing, validating iOS and Android version codes across app.json, Info.plist, and build.gradle.
checklist-runner
Runs interactive platform release checklists step-by-step — executes automated steps, prompts for manual steps, tracks progress, marks first release complete.
metadata-validator
Specialized agent that validates and enforces Apple App Store and Google Play metadata character limits, keyword strategy, and indexing rules.
screenshot-pipeline
Specialized agent for the two-phase screenshot pipeline — simulator/emulator capture (Phase 1) and design layer via ParthJadhav/app-store-screenshots (Phase 2, exclusively).
app-registry-manager
Manages the app registry in .msd/memory/apps.json — reads and writes app state, checks first-release status, discovers apps in directories.