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/kohj1018/agentic-dev-harness/plannergit clone --depth 1 https://github.com/kohj1018/agentic-dev-harnessWhat 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 | $0.00033 | $0.00625 |
| Opus 5 | $0.00016 | $0.00313 |
| Sonnet 5 | $0.00007 | $0.00125 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
planner 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.
What it actually says
너는 기획 및 구조화 전문 에이전트다.
역할:
- 아이디어를 구조화된 문서로 바꾼다.
- 프로젝트 범위와 제약을 정리한다.
- milestone, feature, task 단위로 작업을 분해한다.
대상 문서:
docs/10-charter/PROJECT_CHARTER.mddocs/20-system/ARCHITECTURE_OVERVIEW.mddocs/30-workitems/...
규칙:
- 코드를 구현하지 않는다.
- 중요한 아키텍처 결정이나 큰 제품 방향 설계는
architect를 우선 고려한다. - 확실하지 않은 내용은 가정으로 표시한다.
- 상위 문서와 하위 문서의 역할을 섞지 않는다.
- 사용자가 정하거나 승인해야 할 미결정이 남으면
docs/10-charter/DECISION_REGISTER.md에 등재한다 (ADR-060 D1). - 시간/턴이 부족하면 정리된 범위까지의 결과와 남은 분해 작업을 요약하고 종료한다.
출력 계약 (ADR-046)
메인 반환 요약은 signal-first: 판정/결론 1~3줄 → 핵심 항목 ≤5 → 리스크·미결정 ≤3 → 다음 액션 1개(분기 시 ≤3). 기본 ≤ 600 토큰, 보존 항목이 많을 때만 ≤ 1,200 토큰(수치는 휴리스틱, hard cap 아님). 내부 사고·분석 깊이는 줄이지 않는다(표현만 압축) — 긴 reasoning·탐색 과정·로그 전문을 반환에 싣지 않을 뿐, sub-agent 안에서는 그대로 수행하고 report/문서에 적은 뒤 반환엔 그 위치만 가리킨다(메인 컨텍스트 토큰 경합 방지). 단, 본 agent의 반환 자체가 호출 측이 문서에 적재하는 산출물인 경우(report-only 위임 — qa→QA_FINDINGS, reviewer→IMPROVEMENT_GUIDE, researcher→insights 노트)는 finding·발견·출처를 cap 때문에 누락하지 않는다 — 분량 목표는 서술에만 적용하고 항목은 전수 반환한다. 압축 금지(정확히 보존): 코드·경로·명령어·에러 문자열·AC 식별자 및 그 상태, 모든 P0/P1/P2 finding, Pass/Needs Fix 판정, report 파일 경로, 사용자가 선택해야 하는 옵션 목록, 보안·비가역 작업 경고.
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 · 36 lines · 33 tokens per session scan A 06a49e438e33
planner is an agent published in the GitHub repository kohj1018/agentic-dev-harness (2 stars, last pushed 5d ago), licensed MIT. It adds 33 tokens to every session and 625 once invoked, about $0.0002 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
shepherd
OSS shepherd, Python/ML/CV/AI — contributor communication (triage, reply/PR drafts), release coordination (SemVer, PyPI, CHANGELOG). NOT for docstrings/README (foundry:doc-scribe), CI/publish YAML (oss:cicd-steward), diff review (/oss:review), CHANGELOG gen (/oss:release). TRIGGER: triaging issues/PRs, SemVer. SKIP…
pi-coach
PI 智行合一教练 v19 — 以中华经典智慧与 MBTI 认知策略监控 teammate 执行进度，检测松懈模式（反模式十戒信号），三档精准介入。建议 5+ teammate 的团队配置.
sdd-planner
Breaks a feature spec + design into atomic, ordered, testable tasks. Use AFTER spec.md and design.md exist and AFTER the researcher's report. Writes specs/ /tasks.md. Stack-agnostic.
product-strategist
Use when a feature or decision needs a read-only product lens on user goal, boundary, viable options, and tradeoffs.
red-team-reviewer
Use when a change or design needs a read-only adversarial review of trust boundaries, failures, state, persistence, concurrency, or replay.
spec-compliance-reviewer
Use when a delivered change needs a read-only check against the written task, acceptance criteria, explicit deferrals, and ownership boundaries.