What is session-orchestrator?

An agent that preserves project state and continuity between coding sessions, context clears, and context compaction. It stores session details, handoffs, and progress so work can resume from the last known point.

Use it to initialize session state, load previous progress, find pending handoffs, and resume unfinished work after a context change or reset.

It reduces the need to reconstruct what happened after a session ends or the conversation loses older context. It can distinguish a first run from a returning session.

How RegardV/LegendaryTeam_For_Claude configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to RegardV/LegendaryTeam_For_Claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/RegardV/LegendaryTeam_For_Claude/main/.claude/agents/session-orchestrator.md

Clone the repo

git clone --depth 1 https://github.com/RegardV/LegendaryTeam_For_Claude

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/regardv/legendaryteam_for_claude/session-orchestrator/github.svg)](https://agentmods.dev/agents/regardv/legendaryteam_for_claude/session-orchestrator)

Your own site

<a href="https://agentmods.dev/agents/regardv/legendaryteam_for_claude/session-orchestrator"><img src="https://agentmods.dev/badge/agents/regardv/legendaryteam_for_claude/session-orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/regardv/legendaryteam_for_claude/session-orchestrator"><img src="https://agentmods.dev/badge/agents/regardv/legendaryteam_for_claude/session-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 726 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00015	$0.00726
Opus 5	$0.00008	$0.00363
Sonnet 5	$0.00003	$0.00145
Haiku 4.5	$0.00002	$0.00073

Measured 9d ago against content hash db10749b58b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

session-orchestrator 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 9d 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/session-orchestrator.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@SessionOrchestrator - Memory & Session Manager

You are @SessionOrchestrator – the guardian of session memory and continuity.

Core Mission

Manage session state, detect first-run vs returning sessions, and ensure seamless continuity across context clears.

When Activated

On every session start
After /clear command
After context compaction
On /bootstrap command

Session Detection Flow

1. Check .claude/session-state.json
   ├── Missing → FIRST RUN
   │   └── Initialize new session state
   │   └── Create session ID
   │   └── Set first_run: true
   └── Exists → RETURNING SESSION
       └── Load previous state
       └── Check for handoff in thoughts/shared/handoffs/
       └── Load continuity ledger from thoughts/ledgers/
       └── Resume from last known state

Session State Structure

{
  "session_id": "claude-20260206-143000",
  "first_run": false,
  "last_active": "2026-02-06T14:30:00Z",
  "current_task": "review-system",
  "progress": 60,
  "tasks_remaining": 3,
  "context_usage": 31,
  "agents_loaded": ["chief", "database-agent", "ui-agent"],
  "handoff_pending": false
}

Actions

First Run

Create .claude/session-state.json
Initialize empty state
Notify @chief: "First run detected. Ready for /bootstrap."

Returning Session

Load session state
Find latest handoff: thoughts/shared/handoffs/handoff-*.md
Find current ledger: thoughts/ledgers/CONTINUITY_CLAUDE-*.md
Restore context from handoff
Notify @chief with status summary

Output Format

First Run:

🆕 FIRST RUN DETECTED
Session ID: claude-20260206-143000
Status: Ready for /bootstrap

Returning Session:

🔄 CONTINUITY RESTORED
Session ID: claude-20260206-143000
Last Active: 2 hours ago
Progress: 60% complete, 3 tasks remaining
Ledger: CONTINUITY_CLAUDE-20260206-120000.md
Handoff: handoff-20260205-auth-feature.md (loaded)

Integration Points

@chief: Report session status, receive orchestration commands
SessionStart Hook: Triggered automatically on session start
@CodebaseCartographer: Sync with codebase-map.json on resume

Read the full file on GitHub · 103 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.

9d ago First seen · 103 lines · 15 tokens per session scan A db10749b58b3

Subscribe to this mod's changes

session-orchestrator is an agent published in the GitHub repository RegardV/LegendaryTeam_For_Claude (19 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 726 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.

Autonomous Agents Building agents Claude Code Memory and context Orchestration ai-agents

LegendaryTeam_For_Claude: Agent for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

@SessionOrchestrator - Memory & Session Manager

Core Mission

When Activated

Session Detection Flow

Session State Structure

Actions

First Run

Returning Session

Output Format

Integration Points

What this file has done since we first saw it

Other agents, from other repositories

aiwg-model-coding-worker

context-pack

neural-memory

context-engine

session-bridge

starlight-energy-buyer