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 skills add sidiangongyuan/codex-skills-library --skill app-bug-forensicsgit clone --depth 1 https://github.com/sidiangongyuan/codex-skills-libraryWrote 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/skills/sidiangongyuan/codex-skills-library/app-bug-forensics)<a href="https://agentmods.dev/skills/sidiangongyuan/codex-skills-library/app-bug-forensics"><img src="https://agentmods.dev/badge/skills/sidiangongyuan/codex-skills-library/app-bug-forensics/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/skills/sidiangongyuan/codex-skills-library/app-bug-forensics"><img src="https://agentmods.dev/badge/skills/sidiangongyuan/codex-skills-library/app-bug-forensics.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 | $0.00051 | $0.00893 |
| Opus 5 | $0.00026 | $0.00447 |
| Sonnet 5 | $0.00010 | $0.00179 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
app-bug-forensics 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Bug Forensics
Use this skill when a user reports a bug, screenshot, intermittent failure, or confusing app behavior. The goal is root cause first, patch second.
Workflow
-
Preserve the symptom.
- Identify the exact screen, action sequence, visible message, and affected data scope.
- Inspect screenshots and logs when available.
- Do not assume the visible error string names the real failing component.
-
Trace the path.
- Follow the request from UI event to state store, API client, backend route, persistence, sidecar/process boundary, and external provider when relevant.
- Search for all places that can set the visible error state.
- Check whether the failing request still belongs to the current selection.
- For AI failures, identify the exact provider, model, transport, profile, credential source, timeout, and whether the request reached the provider.
-
Classify likely root cause.
- Stale async request or route watcher race.
- Frontend/backend version mismatch or old sidecar process.
- Missing optional capability being treated as fatal.
- Provider protocol, model, key, base URL, or auth mismatch.
- Default AI profile being added when the user selected another profile.
- Long-running provider request blocked behind an unclosable dialog.
- Provider request timed out locally after remote token usage already began.
- Background job result, status, reconnect, or cancellation state was lost.
- Saved credential/profile source disappeared or was overwritten by another profile.
- Data migration/path/access issue.
- UI overlay, selection, scrolling, or layout state bug.
- Result view was hidden or discarded by navigation instead of explicit clearing.
- Installer or process lifecycle half-update.
-
Reproduce minimally.
- Prefer a focused test or local run over broad speculation.
- If the issue is intermittent, add timing, request tokens, or controlled mocked delays to reproduce the race.
- If external provider behavior is suspected, separate mock branch tests from one real minimal connectivity test.
- For charged or slow provider paths, do not auto-retry the full generation while investigating. Probe status and run only minimal real requests.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 91 lines · 51 tokens per session scan A a7dcf71b5b0e
app-bug-forensics is a skill published in the GitHub repository sidiangongyuan/codex-skills-library (8 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 893 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 skills, from other repositories
superloopy-doctor
Use when diagnosing Superloopy doctor, install, wrapper, plugin cache, hook bootstrap, bundled agents, marketplace, Codex, Claude Code, stale-version, evidence-floor, or host-wiring health problems.
debug-assistant
Systematic debugging assistant that helps identify and fix bugs through structured analysis, hypothesis testing, and root cause identification. Use when facing errors, unexpected behavior, or mysterious bugs.
quick-fix
Apply a minimal, targeted fix to a specific bug or issue. Focused on speed and precision - locate the problem, make the smallest correct change, and verify. Not a planning workflow; use for small fixes, patches, and hotfixes.
error-handling
Patterns for robust error handling across TypeScript, Python, and Go. Covers typed errors, error boundaries, retries, circuit breakers, and user-facing error messages. Use when designing error types, retries, circuit breakers, or user-facing failure messages in TypeScript, Python, or Go.
kubernetes-patterns
Kubernetes workload patterns, resource management, RBAC, probes, autoscaling, ConfigMap/Secret handling, and kubectl debugging for production-grade deployments. Use when writing or reviewing Kubernetes manifests, or debugging probes, RBAC, autoscaling, or resource limits.
ai-regression-testing
Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. Use when adding regression coverage to AI-assisted code, or when the same model both wrote…