session-start

session-start is a command for Claude Code from llcoolblaze/claude-boris. It costs 22 tokens per session (640 once invoked), scanned B, original, MIT.

A command that starts a coding session by loading the project's saved context and checking its current status.

In plain words
What is it for?
Reading project notes, recent progress, git status, recent commits, installed tools, open issues, and project instructions at session start.
Why use it?
It reduces the need to reconstruct what happened in an earlier session before continuing work.

Command for Claude Code

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/llcoolblaze/claude-boris/session-start
Clone the repo
git clone --depth 1 https://github.com/llcoolblaze/claude-boris

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 session-start

README.md
[![agentmods](https://agentmods.dev/badge/commands/llcoolblaze/claude-boris/session-start.svg)](https://agentmods.dev/commands/llcoolblaze/claude-boris/session-start)
Your own site
<a href="https://agentmods.dev/commands/llcoolblaze/claude-boris/session-start"><img src="https://agentmods.dev/badge/commands/llcoolblaze/claude-boris/session-start.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 640 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00022 $0.00640
Opus 5 $0.00011 $0.00320
Sonnet 5 $0.00004 $0.00128
Haiku 4.5 $0.00002 $0.00064

Measured 4d ago against content hash fc4f4892eda0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

session-start scanned grade B with 1 finding 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

!`cat .claude/memory/projectContext.md 2>/dev/null | head -40 || echo "📝 No project context - run /memory-init to set up"`
.claude/commands/session-start.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Start

Memory Bank Loading...

Project Context

!cat .claude/memory/projectContext.md 2>/dev/null | head -40 || echo "📝 No project context - run /memory-init to set up"

Active Context (Last Session State)

!cat .claude/memory/activeContext.md 2>/dev/null | head -30 || echo "No active context"

Progress Status

!cat .claude/memory/progress.md 2>/dev/null | grep -A 20 "## In Progress\|## Completed" | head -25 || echo "No progress tracking"

Recent Session

!cat .claude/memory/sessionHistory.md 2>/dev/null | head -40 || echo "No session history"

Project Status

!pwd !git status --short 2>/dev/null || echo "Not a git repo" !git branch --show-current 2>/dev/null !git log --oneline -5 2>/dev/null

Environment Check

!node --version 2>/dev/null || echo "Node not found" !cat package.json 2>/dev/null | jq -r '.name + " v" + .version' 2>/dev/null || echo ""

Open Issues

!gh issue list --state open --limit 5 2>/dev/null || echo ""

CLAUDE.md Quick Reference

!cat CLAUDE.md 2>/dev/null | head -30 || echo "No CLAUDE.md"


Session Initialization Protocol

1. Synthesize Context

From Memory Bank, understand:

  • Project: What is this and what's its purpose?
  • Last Session: What was being worked on?
  • Current Focus: From activeContext.md
  • Pending Items: From progress.md

2. State Summary

Report to user:

📚 Memory Bank Loaded

Project: [Name from projectContext]
Last Session: [Date and summary from sessionHistory]
Last Working On: [From activeContext]
Pending Tasks: [Count from progress]
Current Branch: [Git branch]
Uncommitted Changes: [Yes/No]

Ready to continue where you left off.

3. Update Active Context

Mark session start:

  • Record start timestamp
  • Note current branch
  • Update session state

4. Suggest Next Actions

Based on context:

  • Continue last session's work?
  • Address pending items?
  • Review open issues?
  • Start something new?

Quick Actions

  • Continue last task: Pick up where you left off
  • Check progress: /progress
  • Review decisions: Look at decisionLog.md
  • Start fresh: "What would you like to work on?"

Read the full file on GitHub · 93 lines

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. 4d ago First seen · 93 lines · 22 tokens per session scan B fc4f4892eda0

Subscribe to this mod's changes

session-start is a command published in the GitHub repository llcoolblaze/claude-boris (48 stars, last pushed 7mo ago), licensed MIT. It adds 22 tokens to every session and 640 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.