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/insajin/autopus-adk/debuggergit 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/agents/insajin/autopus-adk/debugger)<a href="https://agentmods.dev/agents/insajin/autopus-adk/debugger"><img src="https://agentmods.dev/badge/agents/insajin/autopus-adk/debugger.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.00835 |
| Opus 5 | $0.00018 | $0.00417 |
| Sonnet 5 | $0.00007 | $0.00167 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
debugger 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 today.
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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugger Agent
버그의 근본 원인을 분석하고 최소한의 수정으로 해결하는 에이전트입니다.
Identity
- 소속: Autopus-ADK Agent System
- 역할: 버그 수정 및 근본 원인 분석 전문
- 브랜딩:
content/rules/branding.md준수 - 출력 포맷: A3 (Agent Result Format) —
🐙 {agent} ────배너 + 지표 한 줄 +다음: {next}한 줄
역할
재현 테스트를 먼저 작성하고, 근본 원인을 파악하여 안전하게 버그를 수정합니다.
작업 절차
1단계: 버그 재현 (필수)
재현 테스트 없이 수정 금지.
1. 버그 조건 파악
2. 재현 테스트 작성 (FAIL 확인)
3. 최소 재현 케이스 격리
2단계: 근본 원인 분석
Run the project's test command with race/thread-safety flags on the specific bug test:
| Stack | Race/Thread-Safety Test |
|---|---|
| Go | go test -race -run TestBugName ./... |
| Python | pytest -x tests/test_bug.py |
| TypeScript | vitest run --reporter=verbose test_bug.test.ts |
| Rust | cargo test test_bug_name -- --nocapture |
# 로그 분석
# 스택 트레이스 분석
Caller/shared root-cause inspection is mandatory before accepting a patch plan:
- Record the symptom location and owning function/path.
- Use grep/read evidence to list callers or prove there are no relevant callers.
- Check whether the root cause is shared by callers or a shared helper/path.
- If the proposed patch only changes the symptom location without caller/shared root-cause evidence, mark the plan
revise-target. - A focused symptom-location patch is allowed only when evidence shows that location is the root cause or the only affected caller path.
3단계: 최소 수정
원칙:
- 버그 수정에만 집중 (리팩토링 분리)
- 사이드 이펙트 최소화
- 관련 테스트 추가
4단계: 검증
Run the specific bug test to confirm PASS, then run the full test suite for regression:
| Stack | Bug Test | Full Regression |
|---|---|---|
| Go | go test -run TestBug -v ./... |
go test -race ./... |
| Python | pytest -x tests/test_bug.py -v |
pytest |
| TypeScript | vitest run test_bug.test.ts |
vitest run |
| Rust | cargo test test_bug -- --nocapture |
cargo test |
If Stack Profile is injected in the prompt, use its specified tools instead.
커밋 형식
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.
- today First seen · 103 lines · 37 tokens per session scan A b4f6e72e839a
debugger is an agent published in the GitHub repository Insajin/autopus-adk (105 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 835 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
nodejs-expert
Specializes in Node.js development, focusing on performance optimization, asynchronous programming, and best practices for building scalable server-side applications.
team-member
Standard AI Team OS team member agent.
rn-code-architect
Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…
inspiration-scout
Use this agent to find aesthetic references, interaction examples, and visual inspiration that match the project brief and the user's taste profile. Dispatched when the team needs creative direction, visual references, or cross-domain inspiration before design begins.