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 Insajin/autopus-adk --skill debugginggit clone --depth 1 https://github.com/Insajin/autopus-adkWrote 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/insajin/autopus-adk/debugging)<a href="https://agentmods.dev/skills/insajin/autopus-adk/debugging"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/debugging/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/insajin/autopus-adk/debugging"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00016 | $0.00735 |
| Opus 5.5 | $0.00006 | $0.00294 |
| Sonnet 5.5 | $0.00003 | $0.00147 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
debugging 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.
What it actually says
Debugging Skill
버그를 체계적으로 재현하고 근본 원인을 분석하여 수정하는 스킬입니다.
핵심 원칙
재현 테스트를 먼저 작성한다. 수정 전에 버그를 재현하는 테스트를 작성하고, 수정 후 테스트가 통과하는지 확인합니다.
디버깅 프로세스
1단계: 버그 재현
1. 버그 재현 조건 파악
- 어떤 입력/상태에서 발생하는가?
- 항상 발생하는가, 간헐적으로 발생하는가?
- 특정 환경에서만 발생하는가?
2. 재현 테스트 작성 (RED)
- 가장 단순한 재현 케이스로 테스트 작성
- 테스트가 실패하는지 확인
// 버그 재현 테스트 — 수정 전 FAIL, 수정 후 PASS
func TestBug_IssueNumber_ReproductionTest(t *testing.T) {
// Given: 버그 발생 조건
// When: 버그 트리거 동작
// Then: 기대한 동작 (현재는 실패)
}
2단계: 근본 원인 분석
도구 활용:
# Go: 레이스 컨디션 탐지
go test -race ./...
# 스택 트레이스 분석
go test -v -run TestBug 2>&1
# pprof 프로파일링
go test -cpuprofile cpu.out -memprofile mem.out
근본 원인 분류:
- 로직 오류: 조건문, 계산 실수
- 경계 조건: 빈 입력, 최대값, 최소값
- 동시성: 레이스 컨디션, 데드락
- 타입/변환: 오버플로우, nil 포인터
- 외부 의존성: API 변경, 설정 오류
Caller/shared root-cause rule:
- 증상 위치(symptom location), owning function/path, caller 목록 또는 grep evidence를 기록합니다.
- caller와 shared root-cause path를 먼저 확인한 뒤 패치 위치를 선택합니다.
- 증상 위치만 패치하고 caller/shared root-cause evidence가 없으면 patch plan을
revise-target으로 표시합니다. - evidence가 증상 위치 자체가 root cause이거나 affected caller가 하나뿐임을 보여줄 때만 focused patch를 허용합니다.
3단계: 최소 수정
원칙:
- 버그 수정에만 집중 (리팩토링 금지)
- 가능한 한 작은 변경
- 사이드 이펙트 최소화
4단계: 검증
# 재현 테스트 통과 확인
go test -run TestBug -v
# 회귀 테스트 실행
go test ./...
# 레이스 컨디션 재확인
go test -race ./...
체크리스트
- 버그 재현 테스트 작성 및 FAIL 확인
- 근본 원인 파악
- caller/shared root-cause path 확인 또는
revise-target기록 - 최소 수정 적용
- 재현 테스트 PASS 확인
- 전체 테스트 스위트 통과
- 커밋 메시지에 버그 이슈 번호 포함
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 First seen · 97 lines · 16 tokens per session scan A 065af540c052
debugging is a skill published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 735 once invoked, about $0.0001 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 skills, from other repositories
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
implement
Use when an approved plan and task list exist and it is time to turn them into working, tested code — the SDD phase after analyze and before verify. Enforces TDD: a failing test comes before the code that makes it pass, one task at a time, appended to a progress ledger that survives compaction. Delegates test tooling…
debug
Use when something is broken — a failing or flaky test, crash, wrong result or regression — and the root cause must be reproduced and proven before any fix. On-demand; callable mid-implement. NOT a feature to spec or build (that is specify/implement), NOT the lint/test gate (that is verify), NOT adversarial diff…
nw-bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.
test-driven-development
Writing code with tests first: RED-GREEN-REFACTOR, reproduce bugs as failing tests before fixing, and avoid testing anti-patterns. Use when implementing behaviour, fixing a defect, or asked to add tests.
rpa-bugfix
Run when the user invokes /rpa-bugfix together with a clear bug description (expected vs actual, reproduction). Reproduction test first, then fix, full test suite, short report. Will not work correctly without the bug details.