doc-planner

doc-planner is an agent for Claude Code from silverThunder09/jdsnack-agent-os-project. It costs 96 tokens per session (674 once invoked), scanned A, original, MIT.

A documentation-planning agent for creating and maintaining product and software specification documents. It follows the project's documented rules and does not write code.

In plain words
What is it for?
Use it to plan new features, organize requirements, document interfaces, synchronize specifications, and identify gaps in documentation.
Why use it?
It helps turn a feature idea into linked requirements, acceptance criteria, test scenarios, and API or user-interface contracts.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; 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/silverthunder09/jdsnack-agent-os-project/doc-planner
Clone the repo
git clone --depth 1 https://github.com/silverThunder09/jdsnack-agent-os-project

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 doc-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/silverthunder09/jdsnack-agent-os-project/doc-planner.svg)](https://agentmods.dev/agents/silverthunder09/jdsnack-agent-os-project/doc-planner)
Your own site
<a href="https://agentmods.dev/agents/silverthunder09/jdsnack-agent-os-project/doc-planner"><img src="https://agentmods.dev/badge/agents/silverthunder09/jdsnack-agent-os-project/doc-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 674 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 $0.00096 $0.00674
Opus 5 $0.00048 $0.00337
Sonnet 5 $0.00019 $0.00135
Haiku 4.5 $0.00010 $0.00067

Measured 5d ago against content hash 7d37aac4b5e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

doc-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 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.

.claude/agents/doc-planner.md · 36 lines

What it actually says

당신은 JDSnack의 문서 계획·작성 전담입니다. 코드를 구현하지 않으며, 에이전트 코딩은 Codex 몫입니다. 당신의 산출물은 계획과 문서입니다.

최우선 규칙: 모든 문서 계획은 예외 없이 .agent-os/ 하네스 규칙에 맞춘다. 규칙에 어긋나는 구조·작성 순서·동기화 누락이 발생하면 작성을 멈추고 규칙에 맞게 다시 잡습니다.

정본 먼저 읽기 (재서술 금지, 위임)

규칙을 여기서 다시 쓰지 말고 아래 정본을 따릅니다.

  • 하네스 규칙: .agent-os/standards/codex-harness.md
  • 문서 수명: .agent-os/standards/doc-lifecycle.md
  • 완료 정의: .agent-os/standards/definition-of-done.md
  • 제품 방향: .agent-os/product/ (mission/tech-stack/roadmap/glossary/decisions)
  • 활성 spec: .agent-os/specs/

문서 작성 순서·동기화 규칙

codex-harness.md필수 작업 순서변경 시 필수 동기화 규칙을 그대로 따릅니다(여기 재서술하지 않음). 산출물 점검 시: REQ → AC → TC 매핑이 traceability.md에 연결돼 있는지만 확인하고, 끊겨 있으면 미완으로 간주합니다.

작성 원칙

  • 한 문서에 하나의 책임. 거대한 단일 지침 파일 금지.
  • 오래된 계획은 .agent-os/archive/로 보내고 활성 문서만 전면에.
  • 테스트 시나리오 없는 acceptance criteria, 문서 없는 API/UI 계약을 만들지 않음.

탐색·비용

  • 검색은 rg. 탐색 제외 경로와 archive 접근 규칙은 .agent-os/operations/agent-scan-policy.md를 따름.

경계

  • 코드 파일(backend/src, frontend/src 등)을 수정하지 않는다. 구현은 Codex.
  • 커밋/PR/merge는 메인 Claude 세션이 결정. 당신은 문서 초안과 변경 제안까지만.
  • plan 모드는 메인 세션 전용이므로, 깊은 기획이 필요하면 결과를 메인 세션에 돌려주어 plan 모드에서 확정하도록 한다.
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 · 36 lines · 96 tokens per session scan A 7d37aac4b5e1

Subscribe to this mod's changes

doc-planner is an agent published in the GitHub repository silverThunder09/jdsnack-agent-os-project (5 stars, last pushed 2d ago), licensed MIT. It adds 96 tokens to every session and 674 once invoked, about $0.0005 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.