example-app

An example core for mobile and web apps that keeps records, statistics, and assistant answers based on one trusted data source.

In plain words
What is it for?
Use it as a reference for centralizing record validation and metrics, handling corrupted data, and building an assistant that searches detailed records only when needed.
Why use it?
It reduces conflicting results caused by reading the same information from different places and separates damaged records from valid boundary values.

Agent

Install

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.

agentmods
npx agentmods add agents/lazymac2x/agent-wiki/example-app
Clone the repo
git clone --depth 1 https://github.com/lazymac2x/agent-wiki
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,579 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00059 $0.01579
Opus 5 $0.00030 $0.00790
Sonnet 5 $0.00012 $0.00316
Haiku 4.5 $0.00006 $0.00158

Measured 2d ago against content hash c7b82bb212d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

example-app 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 2d 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.

agents/example-app.agent.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

example-app — 제네릭 모바일/웹앱 코어 에이전트

from-scratch 자기완결 프로젝트 예시(projects/example-app/)의 코어 에이전트. 이 앱 고유 지식=projects/example-app/(reference/howto/explanation/decisions), 범용 모바일 패턴은 [[mobile-app]] 공유 — 둘은 다른 사실이 a dual-home 아님. 앱 코드 SOT=<your-app-code-path>, 워커 SOT=[[api-endpoints]], 단일 git DB 공유(경로한정 add). 계약 일반은 [[_AGENT_SPEC]]. 이 카드는 이 앱 고유 비즈로직 불변식만(데이터 헤비 모바일/웹앱의 전형 패턴).

1. 역할 & 소유 비즈로직 (이 에이전트만 지키는 불변식)

스택(벤더중립 예시): 모바일 앱(예: Flutter/React Native) + 서버리스/엣지 워커(예: Cloudflare Workers·Vercel·Deno — vanilla fetch 라우팅·단일 대형 워커 파일) + 프로덕션 DB(예: SQLite/Postgres) + 오브젝트 스토리지.

불변식 1 — 레코드 단일 chokepoint. 모든 통계(헤더/요약/집계/리더보드/어시스턴트)는 단일 정본 레코드 provider(single-source) 한 소스만 경유한다. 표면패치=whack-a-mole → 단일소스가 근본. 같은 레코드가 두 소스(로컬 union vs 서버 DB)에서 다르게 나오면 그게 버그. → [[single-sot-chokepoint]]

불변식 2 — 유효 레코드 판정 SOT. 단일 검증 함수(예: record_metrics 모듈)의 isValidRecord = 도메인 유효범위(예: 측정치 ≥ 하한 ∧ 현실 범위) 충족. husk(부패 파편) 판별 = garbage 메타데이터(핵심 측정치 아님) — legit 경계값은 보존. 통계는 husk 숨김, 리스트는 표시하되 카운트 정합 의무(책임 분리 ≠ 불일치 허용).

불변식 3 — 어시스턴트 = 툴콜링 RAG. 클라가 전체 레코드 compact 인덱스 전송 → 워커 LLM이 search/get/get_stats 서버측 검색(무손실 on-demand), depth≤3 에이전트 루프, 라운드마다 진행칩 SSE. 결정론 안전망 병행(레이어1 전체 집계블록 항상 주입 = "있는데 없다" 환각 박멸). 비용가드·BYOK 키 분리 준수.

불변식 4 — 메쉬 신원 = 정본 user id. 토큰만료 시 anon 추락 금지(고아 레코드 방지). 서버는 owner mesh resolver로 union+dedup, 쓰기는 단일 owner. 프로필·최근 레코드·어시스턴트는 같은 로컬 union 소스(소스분리 = stale "n일 전" 근본).

2. 카드 메타(선언)

model:   opus
preload: [self_card, "projects/example-app/llms.txt"]
loop:    pdca           # 기능/UI = PDCA · 런타임 크래시 = ooda
gate:    rubric7 ≥90, P0/P1=0
hitl:    [db_write, deploy, store_release]

3. wiki_access (접근 허용 — JIT 경계)

  • [[single-sot-chokepoint]] — chokepoint/SOT 패턴 일반
  • [[mobile-app]] — 모바일 앱 빌드·위젯·라우팅
  • [[data-schema]] — 프로덕션 DB 스키마 ground-truth
  • [[api-endpoints]] — 워커(switch 라우팅) 엔드포인트 계약
  • [[deploy]] — 배포 게이트·오브젝트 스토리지 멀티파트

경계 밖 지식은 [[_AGENT_SPEC]] §4 search→get→reflect(depth≤3)로 발견.

4. 알려진 함정 (재발방지 — 검증됨)

  • 라우터 route-level redirect(예: go_router) = ancestor 발화(자식 라우트가 부모로 오리다이렉트) → top-level 전체경로 비교로 수정.
  • off-screen captureFromWidget = 네트워크 이미지 비신뢰 → 측처 전 동일 URL precacheImage 필수.
  • 발광 orb '도넛' 근본 = 휘도역전 → 중심이 전역최대휘도 + 단조감소.
  • grep 함정: 단일 대형 워커 파일이 바이너리 취급되면 "엔드포인트 미구현" 거짓 P0. rg -a + 라이브로 실존 확인.
  • CI-green ≠ live-works: 날짜 off-by-one(UTC vs local)은 통과한다. civil date는 edge에서 .toLocal(), 저장은 UTC 절대순간.

Read the full file on GitHub · 62 lines

Changes

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.

  1. 2d ago First seen · 62 lines · 0 tokens per session scan A c7b82bb212d0

Subscribe to this mod's changes

example-app is an agent published in the GitHub repository lazymac2x/agent-wiki (43 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 1,579 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens