LLM Mart Basic

코드 변경사항 전체 리뷰. code-reviewer 에이전트 + security-audit 에이전트를 순차 실행하는 래퍼 스킬. PR/MR 생성 전 또는 리뷰 요청 시 사용.

코드를 새로 짜기 전에 기존 솔루션(레포 내부 → 사내 미러 → 패키지 레지스트리 → MCP/스킬 → GitHub)을 먼저 검색하는 워크플로. 새 기능/유틸/의존성 추가 직전, "X 기능 넣어줘" 요청에 코드부터 쓰려는 순간 발동. (원본: [affaan-m/ECC](https://github.com/affaan-m/ECC) 의 search-first 스킬, MIT — 이식·번안)

외부 보안팀 코드 검사 전 자체 사전점검. security-audit 에이전트(+ 설정돼 있으면 SonarQube 보안 핫스팟)를 돌려 P0/P1/P2로 정리하고, 발견사항을 이슈로 쪼개 병렬 서브에이전트로 고친다. "보안 검사", "보안 점검", "코드 감사" 언급 시 사용.

스킬 실행 후 피드백을 받아 해당 SKILL.md를 자동 개선하는 메타 스킬. 스킬이 틀렸거나 누락이 있을 때, 또는 새로 배운 함정을 기록할 때 사용.

프로젝트 상태 한눈에 보기. Git 상태·빌드·테스트·최근 이슈·브랜치 현황을 한 번에 조회. 작업 시작 전 또는 상태 점검 시 사용.

Bring documentation back in line with the code after changes to behavior, paths, versions, or generated output. Use on "update the docs", "refresh the README", "docs are stale", and right before opening a PR that changed any of those. Checks each documented claim against the actu

Duplicate this file to create a project skill. Write the trigger condition concretely in the description.

Use when the user invokes /grill-me or asks to have an idea, feature request, or spec grilled, stress-tested, interrogated, or challenged before implementation. Opt-in alternative to superpowers:brainstorming — the user picks one or the other per task.

Fact-check an agent's persistent memory against ground truth — verify each memory's load-bearing claims against code, database, issue tracker and filesystem, correct the stale ones, and report dead ones as archive candidates. Use when memory grows past ~30 files, right after a bi

Full review of code changes. A wrapper skill that runs the code-reviewer agent and the security-audit agent in sequence. Use before creating a PR/MR or when a review is requested.

A workflow that searches for an existing solution (this repo → internal mirrors → package registries → MCP/skills → GitHub) before writing new code. Triggers right before adding a new feature/utility/dependency, or the moment a "add feature X" request tempts you to jump straight

Self-run security pre-check ahead of an external security-team code audit. Runs the security-audit agent (plus SonarQube security hotspots when configured), grades findings P0/P1/P2, splits them into issues, and fixes them with parallel subagents. Use on "security check", "securi

A meta-skill that takes feedback after a skill runs and automatically improves the corresponding SKILL.md. Use when a skill was wrong or incomplete, or to record a newly discovered gotcha.

See project status at a glance. Checks Git status, build, tests, recent issues, and branch status all at once. Use before starting work or when checking on status.

Imported from leeyudok/agents-scaffold/.claude/agents/README.md.

다른 서브에이전트를 실제로 써본 후 피드백을 받아 해당 agents/*.md를 자동 개선하는 메타 에이전트. 에이전트가 틀렸거나, 결과가 부실하거나, description이 실제 동작과 안 맞을 때, 또는 새로 배운 함정을 기록할 때 호출.

머지 전 코드 변경을 버그·보안·품질 관점으로 리뷰. CRITICAL 발견 시 차단 권고.

DB 스키마 변경 안전성 검증. ALTER TABLE 전 위험도 평가·롤백 SQL 생성·FK 정합성 체크. 마이그레이션 파일 추가·수정 시 호출.

기획서/이슈 기준 최소 스코프 구현 전담. 테스트 작성·실행은 하지 않음(sdlc-tester 담당). /sdlc-cycle 커맨드의 개발 단계 서브에이전트.

이슈의 AC/TC 기준 테스트 코드 작성 전담. 구현 코드 수정·테스트 실행은 하지 않음(sdlc-verifier 담당). /sdlc-cycle 커맨드의 테스트 단계 서브에이전트.

Fourteen posts of being wrong in production, compressed to checkboxes

Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds

Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.

Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.

A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.

A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.

None of the safety came from the model. It came from six boring habits.

Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.

Six hours in, one step left, everything green, and the incident that didn't happen

CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

An API request routing a model's tool call through an approval gate to a remote MCP server

31 config keys, two audits, and why the first one was wrong in both directions

The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.

The most important rule wasn't about what I could change. It was about what I was allowed to display.

Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.

{{SKILL_ENTRY:refactor}}

{{SKILL_ENTRY:release}}

Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR.

Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or {{CMD:feature}}.

Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops.

Daily repo hygiene — review the day's repo state, then perform the cleanups under per-action confirmation. Fast-forward only, never destructive without a yes.

Show the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only.

Wire codeArbiter's statusline into ~/.claude/settings.json, or remove it.

The sanctioned task-board mutator — add a queued task, start one (flips to in-progress and stamps the date, minting a dotted ID on pick-up), or mark an in-progress task done. The only blessed write to open-tasks.md.

{{SKILL_ENTRY:security-architecture}}

{{SKILL_ENTRY:tribunal}}

Watch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges.

Copy a file OUT of a running sandbox box to the host — host-initiated egress only (docker cp). The reverse, a host→container bind, is impossible by construction.

Tear down a sandbox box — remove its container and named volume. --keep-volume leaves the volume; with no id, prune reclaims any leaked ca.sandbox=1-labeled object. Cached images are retained.

Run a single command inside a running sandbox box and capture a JSON result — exitCode, separate stdout/stderr, and a truncated flag past the byte cap. The scriptable exec seam.

Open an interactive shell inside a running sandbox box at /work/repo. Read-only root, non-root user, no host-FS access — explore the untrusted code interactively, then exit.

Pull an untrusted repo into an ephemeral, host-FS-isolated Docker container — clone into a named volume, build a dep-cached image, run under structural isolation. Network defaults to offline. Requires Docker and nixpacks.

Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.

Inspect ADR health read-only; optionally select one ADR with --adr N.

Record user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.

Your efficient agentic AI coding CLI assistant

AI coding with Aegis governance built into execution: baseline-aware changes, evidence-backed delivery. Free desktop client, your choice of model. 将哲科思维融入 AI 开发…

Android in docker solution with noVNC supported, video recording, mcp server and AI-agent

Your AI assistant, built for the agentic era. Open source and local: talk to it, and it runs your agents, your coding CLIs, your browser and your apps. Windows,…

Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.

Let Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw CDP as short commands, no screenshots and no MCP ne…

Unofficial, agent-friendly Mercadona shopping CLI (Go) — search products, read prices, build a cart and prepare checkout from the terminal. BYO credentials.

Local-first AI canvas for visual workflows, AI short drama, image/video generation, storyboarding and asset management. ComfyUI, AI agents, MCP & Blender. 本地优先…

Let any AI coding tool — Claude Code, Cursor, Codex — drive your real Chrome. One-prompt setup, muscle memory, local-first.

runs anywhere. uses anything