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 auto-fixgit 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/auto-fix)<a href="https://agentmods.dev/skills/insajin/autopus-adk/auto-fix"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/auto-fix/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/auto-fix"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/auto-fix.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 | $0.00019 | $0.00564 |
| Opus 5 | $0.00010 | $0.00282 |
| Sonnet 5 | $0.00004 | $0.00113 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
auto-fix 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 9d 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
auto-fix — 버그 수정 스킬
OMP Invocation
/auto fix .../auto-fix ...- Load detail skill
auto-fixfor either entrypoint.
프로젝트: autopus-adk | 모드: full
설명
버그를 재현하고 최소한의 변경으로 수정합니다. 재현 테스트를 먼저 작성합니다.
사용법
/auto fix "버그 설명"
/auto fix --file path/to/file
/auto fix "회귀 버그" --auto
플래그
| Flag | Description |
|---|---|
--file <path> |
수정 범위를 특정 파일로 좁힙니다. |
--auto |
확인 단계 없이 바로 수정 흐름을 진행합니다. |
절차
- 버그 재현 테스트 작성 (먼저)
- 테스트 실패 확인
- symptom location, owning function/path, caller 목록 또는 grep evidence 확인
- caller/shared root-cause path 확인 후 패치 위치 결정
- 최소 코드 변경으로 수정
- 테스트 통과 확인
- 전체 테스트 스위트 실행
규칙
- 재현 테스트 없이 수정하지 않음
- 버그 범위 외 코드 변경 금지
- caller/shared root-cause evidence 없이 증상 위치만 고치는 계획은
revise-target으로 표시 - focused patch는 증상 위치가 root cause이거나 affected caller가 하나뿐이라는 근거가 있을 때만 허용
- final response에는 caller/shared root-cause checked, focused patch target, minimum sufficient verification을 receipt로 요약
- 전체 복구/후속 가이드는
/auto fix ...라우터 본문을 우선합니다.
Branding Formats
Error Recovery (show on fix failures)
✗ {subcommand} 실패: {error description}
복구 옵션:
1. 오류 내용을 확인하고 재시도: /auto fix {args}
2. /auto doctor (시스템 상태 진단)
Next Step Auto-Detection (show after fix completes)
다음 단계: {recommendation}
Detection order:
- SPEC status
implemented→✓ 구현 완료 → /auto sync {SPEC-ID} - SPEC status
approved→✓ SPEC {SPEC-ID} 승인됨 → /auto go {SPEC-ID} - No SPEC context → recommend running
/auto reviewto verify the fix
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.
- 9d ago First seen · 77 lines · 19 tokens per session scan A c040a02d2299
auto-fix is a skill published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 564 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
preflight
Plan-vs-codebase validation — verifies API contracts, type names, field accuracy, dependencies, and paths before implementation begins.
error-handling
Error handling patterns for Python and TypeScript applications. Use when designing error hierarchies, implementing retry logic, building error boundaries, or establishing logging strategies. Covers custom exceptions, result types, circuit breakers, and user-facing error messages.
db-testing
Test, debug, and validate database connectivity and queries. Use when diagnosing connection errors, testing configurations, or validating queries before deployment.
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.
triage-issue
Analyze a GitHub issue, verify claims against the codebase, and close invalid issues with a technical response.
atmos-diagnostics
Atmos diagnostics: machine-readable JSONL event streams, diagnostics.enabled/file/includeoutput, subprocess start/end/output events, masking, and debugging Atmos execution.