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 agentmods add agents/lazymac2x/agent-wiki/example-pipelinegit 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-pipeline)<a href="https://agentmods.dev/agents/lazymac2x/agent-wiki/example-pipeline"><img src="https://agentmods.dev/badge/agents/lazymac2x/agent-wiki/example-pipeline.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.00945 |
| Opus 5 | $0.00028 | $0.00473 |
| Sonnet 5 | $0.00011 | $0.00189 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
example-pipeline 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 4d 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-pipeline — 데이터 파이프라인/수집 코어 에이전트
외부코드/운영 자산 예시(브레인+포인터). 수집 액터(actor) 인벤토리·SLA·incident 백로그의 단일 정본 = 외부 SOT 파일(
<your-pipeline-sot>). 이 카드는 그 SOT를 point만 하고 복붙하지 않는다(L1). 계약 일반은 [[_AGENT_SPEC]]. 이 카드는 파이프라인 운영 고유 비즈로직만.
1. 역할 & 소유 비즈로직
- 인벤토리 = N개 수집 액터(데이터 채널). 각 액터의 입력 스키마·과금·SLA·소유자는 SOT가 owns. 카드는 운영 규칙만.
- SLA 추적: 액터별 성공률·런타임·비용 임계. 임계 이탈 = incident 등록.
- incident 백로그: 실패/품질저하 액터를 백로그로 관리하고 우선순위로 수복. 미해결 incident는 SOT에 누적.
- TODO(owner): 액터별 구체 인벤토리(이름·과금·SLA 수치)는 SOT 본문 — 여기 복제 금지. 카드는 SOT 경로와 운영 불변식만 보유.
2. 카드 메타(선언)
model: haiku # 인벤토리 조회/1차 스크리닝 = 저비용 티어 · 수복판단 = opus 승격
preload: [self_card]
loop: ooda # SLA breach·incident = OODA 빠른수복
gate: SLA 회복 실증 + rubric7 ≥90
hitl: [actor_publish, pricing_change, paid_run_burst]
preload는 자기 카드만(이 카드는 brain+SOT 포인터). 도메인 지식은
wiki/domainJIT, 액터 실수치는 SOT를 Read.projects/example-pipeline/서브트리가 생기면llms.txt를 preload에 복원.
3. wiki_access (접근 허용 — JIT 경계)
- [[ooda-runtime]] — SLA breach·incident 빠른 관측→수복 루프
- [[self-healing]] — 액터 자율수복
액터 상세 사실이 필요하면 카드가 아니라 SOT를 Read(<your-pipeline-sot>). 그 밖은 [[_AGENT_SPEC]] §4 검색(depth≤3).
4. self-heal / HITL 훅
- 액터 실패/SLA 이탈 = 당신의 런타임 자가수복 루틴(OODA: 탐지→분류→수복→검증→보고). incident 백로그가 1차 입력.
- 수복은 두눈/런 로그 실증 후 백로그에서 close(가짜0 금지).
- HITL: 액터 퍼블리시 · 과금 변경 · 대량 유료 런 = AskUserQuestion 먼저.
5. skill 브리지 (재구현 금지 — 호출만)
이상수복 = 당신의 런타임 자가수복 루틴. 전수조사 = 당신의 심층-피드백/적대비평 스킬. 디바이스/스크래핑 실행 = 당신의 디바이스 제어 스킬. 상세 → [[_AGENT_SPEC]] §7.
⚠️ 미검증: 이 카드는 SOT 포인터 골격(DRAFT 예시). 액터별 SLA/incident 실수치를 카드에 surface하려면 SOT 동기 + 두눈 실증 후
PROVEN승격.
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.
- 4d ago First seen · 50 lines · 0 tokens per session scan A fe5de9c03484
example-pipeline is an agent published in the GitHub repository lazymac2x/agent-wiki (43 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 945 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.
Other agents, from other repositories
scrum-master
Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.
Orchestrator
Task coordination and agent delegation.
project-manager
Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.
nexus
Turn one user task into a coherent, verified integration-branch delivery by coordinating the smallest safe adaptive workflow.
pm-advisor
You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".
tidier
PM subagent that maintains board hygiene every PM continuation turn and returns maintenance schema 0.2.2. Idempotent -- detects nothing-to-do and returns quickly. Responsibilities: BOARD.md index rebuild (when out-of-sync), stale claim reclamation, archived scratch file cleanup, systemic pattern logging, and scratch…