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/n24q02m/claude-plugins/debug-issuenpx skills add n24q02m/claude-plugins --skill debug-issuegit clone --depth 1 https://github.com/n24q02m/claude-pluginsWhat 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 | $0.00023 | $0.01457 |
| Opus 5 | $0.00012 | $0.00728 |
| Sonnet 5 | $0.00005 | $0.00291 |
| Haiku 4.5 | $0.00002 | $0.00146 |
Grade A, and why
debug-issue 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.
This is a copy
100% identical to debug-issue — 0 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Issue
Systematic debugging using domain-specific decision trees. Start by identifying the symptom category, then follow the corresponding tree.
Category Detection
Map user's symptom to the right tree:
| Symptom keywords | Category |
|---|---|
| "pass through", "no collision", "overlap", "stuck", "slides off" | Physics |
| "signal not firing", "not connected", "callback not called" | Signals |
| "invisible", "not showing", "behind", "flickering", "wrong color" | Rendering |
| "not moving to target", "path wrong", "stuck on nav", "no path" | Navigation |
| "key not working", "input ignored", "wrong button", "double input" | Input |
Physics Decision Tree
Check in this order -- each step is the most common cause at that point:
-
Collision layer/mask mismatch (most common):
- Check defined layer names:
physics(action="layers") - Check node properties:
nodes(action="get_property", scene_path="<scene>.tscn", name="<body>", property="collision_layer") nodes(action="get_property", scene_path="<scene>.tscn", name="<body>", property="collision_mask") - Rule: Object A detects Object B only if A's
collision_maskhas a bit that matches B'scollision_layer. Both must be set correctly.
- Check defined layer names:
-
Missing CollisionShape2D/3D:
- Inspect the scene tree:
scenes(action="info", scene_path="<scene>.tscn") - Verify every physics body and Area has a CollisionShape child. A body without a shape = invisible to physics.
- Inspect the scene tree:
-
Wrong body type:
StaticBody2D: immovable (walls, floors)CharacterBody2D: player/NPC movement viamove_and_slide()RigidBody2D: physics-driven (projectiles, debris)- Common mistake: using
RigidBody2Dfor a player character, then fighting the physics engine
-
Script velocity issues:
- Read the script:
scripts(action="read", script_path="res://scripts/<name>.gd") - Check if
velocityis being set beforemove_and_slide() - Check if gravity is applied in
_physics_process(not_process) - Check if
deltais used for frame-independent movement
- Read the script:
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 · 142 lines · 23 tokens per session scan A 9cb105460376
debug-issue is a skill published in the GitHub repository n24q02m/claude-plugins (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,457 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to debug-issue, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
fab
Search Fab's public free catalog (including Quixel Megascans) and directly import eligible assets without adding them to the account library, or discover/import the signed-in Epic account's owned Fab library. Use for free Fab/Quixel searches, owned-library questions, compatibility checks, and Fab imports. No…
persona-triggers
페르소나 v5 트리거 상세(AT 20패턴 + 15관점 매핑·매칭 예시). 관점·객관적·철저·깊이·검증·추천·디버깅·방향·진행·근거·출처·사례·팩트·증거 등 트리거 단어 감지 시 상세 참조.
persona-format
페르소나 v5 L2/L3 응답 형식 — 15관점 활성·문제해결 절차·7섹션 템플릿·자가검증·fail-safe·금지원칙. 코드 변경·디버깅·구현 등 L2/L3 작업 시 로드.
persona-accountant
15년+ 회계·세무 전문가 페르소나(#14) 깊은 도메인. 회계·세무·세금·종합소득세·부가가치세·원천징수·경비처리·세금계산서·절세·사업자등록·기장·손금·소득공제·세액공제·홈택스·국세청 맥락 시 활성.
persona-marketer
15년+ 마케팅·세일즈 전문가 페르소나(#15) 깊은 도메인. 마케팅·세일즈·카피·콘텐츠·SEO·광고·랜딩페이지·전환·퍼널·브랜딩·포지셔닝·리드·캠페인·리텐션·그로스·어카운트·컨설팅 맥락 시 활성.
persona-safety
페르소나 v5 안전 작업 — 보안 always-on·비가역 작업 게이트·코드 메타규칙·모바일 UI(375px) 검증·외부도구 도입검토. 코드/UI/보안/배포/삭제/force push 작업 시 로드.