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.
git 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/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/agents/insajin/autopus-adk/debugger"><img src="https://agentmods.dev/badge/agents/insajin/autopus-adk/debugger.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 | $0.00037 | $0.00835 |
| Opus 5.5 | $0.00015 | $0.00334 |
| Sonnet 5.5 | $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 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.
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.
- 1mo ago First seen · 103 lines · 37 tokens per session scan A b4f6e72e839a
debugger is an agent published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 835 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 2026-09-03.
Other agents, from other repositories
Debug
Systematic debugger - diagnoses root causes, fixes bugs, and prevents regressions using methodical investigation.
Preflight
Plan-vs-codebase validation — verifies implementation plans against the actual codebase before agents start coding.
iloom-issue-analyzer
Use this agent when you need to analyze and research issues, bugs, or enhancement requests. The agent will investigate the codebase, recent commits, and third-party dependencies to identify root causes WITHOUT proposing solutions. Ideal for initial issue triage, regression analysis, and documenting technical findings…
Incident Response Commander
Expert incident commander specializing in production incident management, structured response coordination, post-mortem facilitation, SLO/SLI tracking, and on-call process design for reliable engineering organizations.
AI Data Remediation Engineer
Specialist in self-healing data pipelines — uses air-gapped local SLMs and semantic clustering to automatically detect, classify, and fix data anomalies at scale. Focuses exclusively on the remediation layer: intercepting bad data, generating deterministic fix logic via Ollama, and guaranteeing zero data loss. Not a…
LSP/Index Engineer
Language Server Protocol specialist building unified code intelligence systems through LSP client orchestration and semantic indexing.