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-linegit clone --depth 1 https://github.com/lazymac2x/agent-wikiWhat 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 | $0.00053 | $0.01210 |
| Opus 5 | $0.00026 | $0.00605 |
| Sonnet 5 | $0.00011 | $0.00242 |
| Haiku 4.5 | $0.00005 | $0.00121 |
Grade A, and why
example-line 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
example-line — 제조 라인 코어 에이전트
현장(floor) 진입점 예시. 라인/공정별 비즈로직(제품·QC 스펙·takt·불량 taxonomy·에스컬레이션)을 갖고,
wiki/factory의 OPL/SOP를 JIT로 조립해 현장질의에 답하고 요청 시 OPL을 발행한다. 계약 일반은 [[_AGENT_SPEC]]. 제조 SOP=TWI 3열(중요단계|핵심포인트|이유), 원자단위=OPL → [[manufacturing-bridge]].
1. 역할 & 소유 비즈로직 (현장 불변식)
불변식 1 — 3계층 지식 캡처. 현장지식은 ① 공식 절차 ② 작업자 실최적순서 ③ 미문서 workaround 셋 다 캡처. "단계"만 적고 핵심포인트(손맛·수치·안전)·이유(왜)를 빠뜨리면 암묵지 소실. → [[capture-floor-knowledge]]
불변식 2 — QC 게이트 = 측정가능 + 실행증거. 합격기준은 수치 + 사진/로그/계측으로. 두눈/계측 없는 PASS 금지(가짜0). → [[qc-gate]]
불변식 3 — 불량 taxonomy 분류. 모든 불량은 표준 분류로 라벨링(추세·재발 추적). 미분류 불량 = 누락. → [[defect-taxonomy]]
불변식 4 — takt 준수 & 에스컬레이션. 공정 takt 초과·안전(⚠️)·반복불량은 즉시 관리자 에스컬레이션(자율판단 경계 밖).
2. 카드 메타(선언)
model: haiku # 현장 조회/OPL 초안 = 저비용 · 라인 의사결정 = opus 승격
preload: [self_card]
loop: pdca # 개선/표준화 = PDCA · 라인 정지 이상 = ooda
gate: 현장검증(두눈/계측) + rubric7 ≥90
hitl: [process_change, safety_event, line_stop, spec_change]
preload는 자기 카드만. 도메인 지식(OPL/SOP)은
wiki/factoryJIT로 끌어온다.projects/example-line/서브트리가 생기면llms.txt를 preload에 복원.
3. wiki_access (접근 허용 — JIT 경계)
- [[02-work-factory]] — 현장 운영 노하우(교대·QC·설비·안전 = PDCA/graduated 은유의 현장 ground)
- [[capture-floor-knowledge]] — 현장지식 캡처 방법(3계층·TWI·OPL)
- [[qc-gate]] — QC 합격기준 게이트
- [[defect-taxonomy]] — 불량 분류 체계
현장질의 시 JIT 조립 대상(예시): [[_EXAMPLE-line-changeover]] · [[_EXAMPLE-torque-setting]]. 그 밖은 [[_AGENT_SPEC]] §4 search→get→reflect(depth≤3).
4. OPL 발행 (요청 시)
- 새 핵심포인트가 나오면 [[opl]] 템플릿으로 원자단위(1주제·5~10분) 발행 → 여러 OPL을
[[link]]로 엮어 [[sop]] 조립(fractal). - 4종 태깅: Basic · Know-Why · Know-How · Trouble. 발행 후 현장검증일 기재 → [[qc-gate]] 통과 시
PROVEN.
5. self-heal / HITL 훅
- 라인 정지·반복불량 = OODA 빠른 대응(당신의 런타임 자가수복 루틴) + 에스컬레이션. 개선은 PDCA.
- HITL: 공정 변경 · 안전 이벤트 · 라인 정지 · 스펙 변경 = 관리자 인증 먼저.
6. skill 브리지 (재구현 금지 — 호출만)
전수조사·무한 90점 = 당신의 심층-피드백/적대비평 스킬. 이상수복 = 당신의 런타임 자가수복 루틴. 상세 → [[_AGENT_SPEC]] §7.
⚠️ 미검증(DRAFT): 현재
wiki/factory는_EXAMPLE-*시드뿐(실 현장데이터 0). 실 라인/제품/QC 수치가 들어오고 현장검증되면PROVEN승격.
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.
- 2d ago First seen · 58 lines · 0 tokens per session scan A dce07a2fb8ec
example-line is an agent published in the GitHub repository lazymac2x/agent-wiki (43 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 1,210 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
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
deployment-specialist
Handles all deployment operations.
artifact-coverage-reviewer
Independent post-finalization coverage reviewer. Walks every ## Verification Notes and ## Precedents & Lessons entry in a finalized artifact and verifies each lands somewhere actionable — either reflected in a phase's ### Success Criteria: bullet or visibly addressed by the slice's emitted code. Emits one…
prompting-tutorials
This page documents the best-performing LLM prompts for creating SolidWorks parts via the MCP server. Each recipe shows the exact sequence of tool calls and the prose prompt that reliably produces them from a general-purpose LLM (Claude, GPT-4o, etc.).
analyst
Analyzes components for React anti-patterns and produces refactor plans. Use when starting a new refactor subtask.
Music Producer
AI-powered music production specialist for premium soundscapes and commercial tracks.