start-session

A session-start command that acts as a project manager for Cursor, an AI coding editor, and helps decide what to work on next.

In plain words
What is it for?
It reads planning and instruction files, checks recent Git changes, proposes a task with acceptance conditions and risks, and can prepare a handoff to Claude Code.
Why use it?
It gathers the project state and narrows it to one clear priority, so a coding session can begin with a concrete goal.

Command

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 commands/chachamaru127/claude-code-harness/start-session
Clone the repo
git clone --depth 1 https://github.com/Chachamaru127/claude-code-harness
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 232 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 $0.00018 $0.00232
Opus 5 $0.00009 $0.00116
Sonnet 5 $0.00004 $0.00046
Haiku 4.5 $0.00002 $0.00023

Measured 3d ago against content hash fb5604004ef2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start-session 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 3d 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.

templates/cursor/commands/start-session.md · 32 lines

What it actually says

/start-session

あなたは Cursor (PM) です。目的は「いま何をすべきか」を短時間で明確にし、必要なら Claude Code へ依頼することです。

1) 状況把握(最初に読む)

  • @Plans.md
  • @AGENTS.md
  • @CLAUDE.md

可能なら以下も確認:

  • git status -sb
  • git log --oneline -5
  • git diff --name-only

2) 今日のゴールを決める

次を1つに絞って提案してください:

  • 最優先タスク(1つ)
  • 受入条件(3つ以内)
  • 想定リスク(あれば)

3) Claude Codeに依頼する(必要なら)

タスクを Claude Code に渡す場合、/handoff-to-claude を実行して依頼文を作ってください。

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. 3d ago First seen · 32 lines · 18 tokens per session scan A fb5604004ef2

Subscribe to this mod's changes

start-session is a command published in the GitHub repository Chachamaru127/claude-code-harness (3,079 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 232 once invoked, about $0.0001 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.