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/zakedu/agent-kanban-harness/_templategit clone --depth 1 https://github.com/Zakedu/agent-kanban-harnessWrote 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/zakedu/agent-kanban-harness/_template)<a href="https://agentmods.dev/agents/zakedu/agent-kanban-harness/_template"><img src="https://agentmods.dev/badge/agents/zakedu/agent-kanban-harness/_template.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 5.1 | $0.00002 | $0.00516 |
| Opus 5 | $0.00001 | $0.00258 |
| Sonnet 5 | $0.00000 | $0.00103 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
my-agent 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 5d 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
내 에이전트
이 파일은 교안의 Skill File 5단계 구조로 작성한다. 하네스 안에서 에이전트가 흔들리지 않도록 역할(ROLE), 참조(REFERENCE), 제약(CONSTRAINTS), 출력(OUTPUT), 검증(VALIDATION)을 명확히 고정한다.
1. 역할(ROLE)
<이 에이전트가 어떤 사람처럼 행동해야 하는지 적는다. 예: "결제 흐름만 보는 백엔드 검토자", "문장 톤을 지키는 한국어 편집자".>
2. 참조(REFERENCE)
<에이전트가 반드시 먼저 읽을 파일, 폴더, 골든 데이터, API 문서, playbook을 적는다. 예: CLAUDE.md, golden/input-example.md, docs/payment.md.>
3. 제약(CONSTRAINTS)
<하면 안 되는 일과 경계를 적는다. 예: .env 읽지 않기, config.js 덮어쓰지 않기, owns 밖 파일 수정 금지.>
4. 출력(OUTPUT)
<작업이 끝났을 때 남겨야 하는 산출물을 적는다. 예: 수정 파일 목록, 검증 명령 결과, reportSummary, 다음 task 제안.>
5. 검증(VALIDATION)
<완료 판정 기준을 적는다. 예: npm test 통과, 골든 데이터 입력으로 기대 출력과 비교, 사람검토가 필요한 조건.>
Task 작성 규칙
- 모든 작업은 먼저 칸반 task로 등록한다.
CLAUDE.md는 마스터 프롬프트다. 작업 전 이 규칙을 따른다.- Claude=컨설턴트(기획·검토), Codex=신입개발자(파일작업) 역할 구분을 유지한다.
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.
- 5d ago First seen · 45 lines · 2 tokens per session scan A d414bb58e2e5
my-agent is an agent published in the GitHub repository Zakedu/agent-kanban-harness (2 stars, last pushed 1mo ago), licensed MIT. It adds 2 tokens to every session and 516 once invoked, about $0.0000 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.