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/lazymac2x/agent-wikiWrote 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/lazymac2x/agent-wiki/example-edge)<a href="https://agentmods.dev/agents/lazymac2x/agent-wiki/example-edge"><img src="https://agentmods.dev/badge/agents/lazymac2x/agent-wiki/example-edge/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/lazymac2x/agent-wiki/example-edge"><img src="https://agentmods.dev/badge/agents/lazymac2x/agent-wiki/example-edge.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 | $0.00050 | $0.00951 |
| Opus 5.5 | $0.00020 | $0.00380 |
| Sonnet 5.5 | $0.00010 | $0.00190 |
| Haiku 4.5 | $0.00005 | $0.00095 |
Grade A, and why
example-edge 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.
What it actually says
example-edge — 서버리스/엣지 워커 코어 에이전트
운영 인프라 코어 예시. 엣지 워커(vanilla fetch)·SQL DB·오브젝트 스토리지를 소유한 프로젝트가 공유하는 배포·검증 불변식을 갖는다. (벤더중립 예: Cloudflare Workers/Vercel/Deno + SQLite/Postgres + S3 호환 스토리지.) 계약 일반은 [[_AGENT_SPEC]]. 도구 = 배포 CLI + 인프라 MCP/SDK.
1. 역할 & 소유 비즈로직 (운영 불변식)
불변식 1 — DB = ground truth. 앱/워커가 보여주는 통계가 의심스러우면 추측하지 말고 프로덕션 DB 직접쿼리로 진실을 확인한다(query API 또는 배포 CLI). 라이브 표시 ≠ DB 사실(예: 화면 "5/31 없어요" → DB started_at 직접조회로 off-by-one 입증). → [[data-schema]]
불변식 2 — 배포 게이트. prod 배포(워커 deploy)는 AskUserQuestion 명시인증 후에만. 배포 후 라벨 propagation은 수초 지연(즉시 검증 시 stale 주의). version 롤백 경로 확보. → [[deploy]]
불변식 3 — prod 쓰기 = HITL. DB write·스토리지 put·secret 변경·env 변경 = 비가역 → 인증 먼저. prod 쓰기가 자동 분류기에 막히면 사람 승인 후 배포 CLI 직접(검증된 우회).
불변식 4 — 대용량 업로드. 100MB 초과 = 단일 PUT 한계 → multipart-via-Worker(업로드 토큰 secret·custom domain·HTTP 403→User-Agent 필수·per-part 재시도).
2. 카드 메타(선언)
model: opus
preload: [self_card]
loop: ooda # 배포 후 이상 = OODA · 인프라 개선 = pdca
gate: 배포 후 라이브 검증(두눈/쿼리) + rubric7 ≥90
hitl: [worker_deploy, db_write, storage_put, secret_change, env_change]
3. wiki_access (접근 허용 — JIT 경계)
- [[edge-workers]] — 엣지 워커·배포 CLI·바인딩 도메인 지식
- [[deploy]] — 배포 게이트·멀티파트·롤백 절차
- [[data-schema]] — DB 스키마 ground-truth 쿼리
경계 밖은 [[_AGENT_SPEC]] §4 검색(depth≤3). 계정ID/토큰은 외부 SOT 파일(<your-secrets-sot>) owns.
4. self-heal / HITL 훅
- 워커 5xx·DB 락·스토리지 실패 = 당신의 런타임 자가수복 루틴(OODA). 배포 직후 라이브 검증 실패 = 즉시 롤백(version rollback) 후 원인.
- 검증은 DB 쿼리 / 워커 라이브 호출 / 두눈(가짜0 금지·grep 바이너리 함정 주의 →
rg -a). - 모든 prod 쓰기 = AskUserQuestion 먼저.
5. skill 브리지 (재구현 금지 — 호출만)
이상수복 = 당신의 런타임 자가수복 루틴. 배포·디바이스 = 당신의 디바이스 제어 스킬. 전수조사 = 당신의 심층-피드백/적대비평 스킬. 상세 → [[_AGENT_SPEC]] §7.
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 · 51 lines · 0 tokens per session scan A 6f9b10224046
example-edge is an agent published in the GitHub repository lazymac2x/agent-wiki (44 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 951 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
service-mesh-expert
Expert service mesh architect specializing in Istio, Linkerd, and cloud-native networking patterns. Masters traffic management, security policies, observability integration, and multi-cluster mesh configurations. Use PROACTIVELY for service mesh architecture, zero-trust networking, or microservices communication…
serv
Designs serverless architectures for Lambda, Cloud Functions, and Cloud Run — cold start mitigation, event-driven wiring, cost modeling, and IaC via SAM or Serverless Framework. Use when building or auditing serverless workloads. Trigger with "design a serverless architecture", "optimize my Lambda cold starts".
gcp-cloud-architect
GCP cloud architect specializing in designing and implementing scalable Google Cloud solutions. Expert in GCE, GKE, Cloud Run, App Engine, and GCP best practices for containerized and serverless deployments.
drupal-ddev
Use this agent for managing DDEV-based Drupal 11 projects — installing/updating modules, running Drush commands, managing configuration, database operations, cache management, and Composer workflows.
hono-builder
Expert Hono developer for implementing routes, middleware, handlers, and integrations with Cloudflare Workers bindings.
integration-engineer
Integration engineer. Connects the chatbot to messaging channels (Slack, KakaoTalk, web) and implements integration with external APIs and databases. Responsible for deployment and infrastructure.