session-start

A command for restoring project context at the start of a work session or after the conversation has been shortened. It loads project memory, the current working plan, and recent session history.

In plain words
What is it for?
Use it to gather saved project information, review the previous session, understand the current plan, and begin a new session with a concise status summary.
Why use it?
It helps the assistant recover what the project is about and what was happening without reconstructing the context manually.

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/agentsea/flashbacker/session-start
Clone the repo
git clone --depth 1 https://github.com/agentsea/flashbacker

Made for: Claude Code.

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 348 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 $0.00348
Opus 5 $0.00000 $0.00174
Sonnet 5 $0.00000 $0.00070
Haiku 4.5 $0.00000 $0.00035

Measured 2d ago against content hash 2dc00f7cbf71, 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.

templates/.claude/commands/fb/session-start.md · 43 lines

What it actually says

Session Start

Manual session recovery after compaction or when starting fresh. Uses the hybrid AI+Computer approach for reliable context gathering.

Task

  1. Gather Context: Run flashback working-plan --context to get:

    • Project memory from REMEMBER.md
    • Current working plan from WORKING_PLAN.md
    • Previous session conversation history (not empty current session)
    • Current session information
  2. Load Context: Use flashback session-start --context to get recent conversation transcript

  3. Understand what you work working on from the conversation transcript, REMEMBER.md, and WORKING_PLAN.md:

    • What this project is about (from REMEMBER.md)
    • What you were working on (from WORKING_PLAN.md)
    • What happened in the last session (from conversation log)
  4. Welcome User: After loading context, provide a brief summary of what you understand about the project and ask "What would you like to work on now?"

Context Gathering Command

The CLI command handles all file reading and context formatting consistently:

flashback working-plan --context && flashback session-start --context

This outputs structured context including:

  • Project memory and key learnings
  • Current development plan and priorities
  • Previous conversation history for continuity
  • Session restoration instructions

Usage Notes

This command is used manually when:

  • Starting work after auto-compact (no PostCompact hook exists)
  • Beginning a fresh session and need project context
  • Hook didn't trigger properly and need manual context restoration

CRITICAL: Gets previous meaningful conversation, not empty current session context.

Usage: /fb:session-start

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 · 43 lines · 0 tokens per session scan A 2dc00f7cbf71

Subscribe to this mod's changes

session-start is a command published in the GitHub repository agentsea/flashbacker (57 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 348 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.