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 skills/mannansaood/termi/debug-rust-panicnpx skills add MannanSaood/termi --skill debug-rust-panicgit clone --depth 1 https://github.com/MannanSaood/termiWhat 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 | $0.00051 | $0.00831 |
| Opus 5 | $0.00026 | $0.00415 |
| Sonnet 5 | $0.00010 | $0.00166 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
debug-rust-panic 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this checklist whenever a cargo test run fails, a panic message
shows up in logs, or behavior doesn't match what a test expects.
1. Reproduce narrowly
cd rust
cargo test <failing_test_name> -- --nocapture
--nocapture shows println!/log output even for passing tests, which
often reveals the actual sequence of events leading to a failure that the
assertion message alone doesn't show.
2. Classify the failure
- Panic with a
.unwrap()/.expect()in the message: this should have been caught byclippy::unwrap_usedbefore it ever ran. Two possibilities:- It's in a
#[cfg(test)] mod testsblock — expected, not a bug, unless the test itself is wrong. - It's in production code — this is a regression in lint coverage.
Check whether the file has
#![warn(clippy::unwrap_used)]inherited fromlib.rs(it should, crate-wide) and whether clippy was actually run before this code was merged (cargo clippy --all-targets -- -D warnings -D clippy::unwrap_used -D clippy::expect_used).
- It's in a
- Poisoned mutex panic (
PoisonErroror "lock" in the message): check whether the code uses.lock().unwrap()instead ofutils::sync_ext::LockExt::lock_safe(). If it's a data buffer (not a mutex protecting a real invariant), switch tolock_safe()— see that module's doc comment for when this is/isn't appropriate. - VFS operation failed unexpectedly: check whether the code called a
FsProvidermethod directly instead of going throughVfsService. If it went throughVfsService, check whether theVfsOutcomewasBlocked(capability check failed — expected for chmod/symlink on SAF) vs. an actual bug. Readvfs/capabilities.rs's capability matrix for the relevantFsTypebefore assuming it's a bug. - JNI-related failure: this can only be meaningfully debugged
on-device or with device logs (
adb logcat). Don't try to reproduce JNI crashes withcargo test— theandroidfeature only type-checks on host, it doesn't give you a JVM to actually exercise those code paths.
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 · 73 lines · 51 tokens per session scan A 7d539c8b8678
debug-rust-panic is a skill published in the GitHub repository MannanSaood/termi (8 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 831 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
sceneview-web
Build 3D and WebXR (AR/VR) experiences in the browser with SceneView for Web — Filament.js (WebGL2/WASM) wrapped in a Kotlin/JS DSL and a plain-JavaScript API on window.sceneview. Use whenever the user asks for "3D in the browser", "a web model viewer", "WebXR AR/VR", or any browser 3D/AR app where the dependency is…
sceneview
Build 3D and AR apps with the SceneView SDK in Jetpack Compose, SwiftUI (iOS/macOS/visionOS via SceneViewSwift), Web (Filament.js), Flutter and React Native. Use whenever the user asks for "3D in Compose", "AR with ARCore in Compose", a model viewer, or any cross-platform 3D/AR app where the dependency is…
sceneview-ios
Build 3D and AR apps on Apple platforms (iOS, macOS, visionOS) with SceneViewSwift — the SwiftUI wrapper around RealityKit. Use whenever the user asks for "3D in SwiftUI", "AR with ARKit in SwiftUI", a model viewer for iOS, or any Apple-platform 3D/AR app where the dependency is the SceneViewSwift Swift Package from…
to-plan
Use when one ready GitHub issue or an in-chat task needs a repository-aware implementation plan for a later implementation workflow.
compose-ui-testing-patterns
Use when writing or reviewing Jetpack Compose UI tests, screenshot tests, previews, semantics assertions, fake image loading, keyboard input, focus assertions, interaction state (hover/pressed/focused), or tests for plain state-driven UI composables.
gradle-run
Use when planning to execute Gradle through gradle, ./gradlew, or a custom gradlew wrapper script, or diagnosing a Gradle build, compact workflow ledger, repeated failure fingerprint, check, test, lint, warning, or failure even when no new Gradle run is appropriate.