my-agent

my-agent is an agent for Claude Code from Zakedu/agent-kanban-harness. It costs 2 tokens per session (516 once invoked), scanned A, original, MIT.

A set of instructions that defines an agent’s role, reference materials, limits, expected output, and checks. An agent is a coding assistant that follows these instructions while working on tasks.

In plain words
What is it for?
Use it to describe what the agent should do, what it must read first, what it must avoid, what it should produce, and how its work is checked.
Why use it?
It gives the agent a fixed working method and clear boundaries, reducing inconsistent decisions or edits in the wrong files.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions CLAUDE.md; mentions Codex.

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/zakedu/agent-kanban-harness/_template
Clone the repo
git clone --depth 1 https://github.com/Zakedu/agent-kanban-harness

Made for: Claude Code.

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 my-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/zakedu/agent-kanban-harness/_template.svg)](https://agentmods.dev/agents/zakedu/agent-kanban-harness/_template)
Your own site
<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>
Per session 2 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 516 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 5.1 $0.00002 $0.00516
Opus 5 $0.00001 $0.00258
Sonnet 5 $0.00000 $0.00103
Haiku 4.5 $0.00000 $0.00052

Measured 5d ago against content hash d414bb58e2e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

agents/_TEMPLATE.md · 45 lines

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.
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. 5d ago First seen · 45 lines · 2 tokens per session scan A d414bb58e2e5

Subscribe to this mod's changes

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.