session-start

A workflow for starting a documented coding session with Claude Code’s memory files. It records the session context, Git state, goals, and progress in project or personal notes.

In plain words
What is it for?
Use it at the beginning of work when you want to document the session, inspect existing memory files, and define its goals.
Why use it?
It gives later sessions a written record of what was happening, reducing the need to reconstruct context from scratch.

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/brennercruvinel/ccplugins/session-start
Clone the repo
git clone --depth 1 https://github.com/brennercruvinel/CCPlugins
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 256 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 $0.00000 $0.00256
Opus 5 $0.00000 $0.00128
Sonnet 5 $0.00000 $0.00051
Haiku 4.5 $0.00000 $0.00026

Measured 2d ago against content hash f9177979e764, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-start 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.

commands/session-start.md · 28 lines

What it actually says

Start Coding Session

I'll begin a documented coding session using Claude Code CLI's memory system.

I'll integrate with the native memory system by updating CLAUDE.md:

  • Session timestamp and context
  • Current git state and branch
  • Session goals and objectives
  • Progress tracking throughout our work

Let me check for existing memory files and update them appropriately:

  • Project memory (./CLAUDE.md) for team-shared context
  • User memory (~/.claude/CLAUDE.md) for personal session tracking

Please tell me:

  1. What are we working on today?
  2. What specific goals do you want to accomplish?
  3. Any context I should know about?

I'll add this session context to your memory system using the /memory command functionality, ensuring our progress is tracked and can be resumed later. This integrates seamlessly with Claude Code CLI's native memory management rather than creating a separate system.

Important: I will NEVER:

  • Add "Co-authored-by" or any Claude signatures
  • Include "Generated with Claude Code" or similar messages
  • Modify git config or user credentials
  • Add any AI/assistant attribution to the commit

The session context will be preserved in the appropriate CLAUDE.md file for future reference and continuation.

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. 2d ago First seen · 28 lines · 0 tokens per session scan A f9177979e764

Subscribe to this mod's changes

session-start is a command published in the GitHub repository brennercruvinel/CCPlugins (2,780 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 256 tokens. 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.