example-pipeline

example-pipeline is an agent for coding agents from lazymac2x/agent-wiki. It costs 55 tokens per session (945 once invoked), scanned A, original, MIT.

An example agent for running data-collection pipelines, where separate collectors gather data from different channels. It tracks each collector's owner, service targets, failures, and recovery work using an external source of truth.

In plain words
What is it for?
Use it as a reference for monitoring collectors, recording failures, prioritising recovery, and handling approval-sensitive actions such as publishing collectors or changing prices.
Why use it?
It keeps operational details in one authoritative place instead of copying them into the agent's instructions. It also provides rules for noticing service-level breaches and managing unresolved incidents.

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-pipeline
Clone the repo
git clone --depth 1 https://github.com/lazymac2x/agent-wiki

Wrote 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.

agentmods badge for example-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/agents/lazymac2x/agent-wiki/example-pipeline.svg)](https://agentmods.dev/agents/lazymac2x/agent-wiki/example-pipeline)
Your own site
<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>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 945 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 $0.00055 $0.00945
Opus 5 $0.00028 $0.00473
Sonnet 5 $0.00011 $0.00189
Haiku 4.5 $0.00006 $0.00094

Measured 4d ago against content hash fe5de9c03484, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

agents/example-pipeline.agent.md · 50 lines

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/domain JIT, 액터 실수치는 SOT를 Read. projects/example-pipeline/ 서브트리가 생기면 llms.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 PROVEN 승격.

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. 4d ago First seen · 50 lines · 0 tokens per session scan A fe5de9c03484

Subscribe to this mod's changes

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.