session-state

A session manager that saves and reloads the state of an ongoing multi-agent coding session in project files. It also keeps archived session history.

In plain words
What is it for?
Use it to save, load, resume, or review orchestrator sessions. An orchestrator coordinates multiple coding agents working on a project.
Why use it?
It helps continue work after a disconnect or interruption without rebuilding the session context manually.

Skill for Claude CodeCodex

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 skills/data-wise/craft/session-state
Any agent
npx skills add Data-Wise/craft --skill session-state
Clone the repo
git clone --depth 1 https://github.com/Data-Wise/craft

Made for: Claude Code, Codex.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,876 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 $0.00050 $0.01876
Opus 5 $0.00025 $0.00938
Sonnet 5 $0.00010 $0.00375
Haiku 4.5 $0.00005 $0.00188

Measured yesterday against content hash ac599e9c82e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-state 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 yesterday.

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.

skills/orchestration/session-state/SKILL.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session State Manager

Handles persistent state for orchestrator sessions, enabling resume after disconnects.

Scope — Not to Be Confused With orchestrate:resume

"Resume" here means resuming orchestrator-v2 session state: reloading .claude/orchestrator-session.json so an in-progress multi-agent orchestration can continue where it left off (see Resume Flow below). This skill has no relationship to the orchestrate:resume slash command, which was a separate, fictional 523-line command removed in #239. If a request seems to want "bring back the old orchestrate:resume command," that is out of scope for this skill — this skill only manages the session-state JSON files described below.

State File Location

.claude/orchestrator-session.json     # Current session (project-local)
.claude/orchestrator-history/         # Session history (project-local)
  └── 2025-12-27-abc123.json         # Archived sessions

Session State Schema

{
  "schema_version": "1.0",
  "session_id": "2025-12-27-abc123",
  "created": "2025-12-27T10:30:00Z",
  "updated": "2025-12-27T11:45:00Z",
  "project": {
    "name": "my-project",
    "path": "/path/to/my-project",
    "git_branch": "dev"
  },
  "goal": "Add sensitivity analysis to RMediation::medci()",
  "mode": "default",
  "status": "in_progress",
  "agents": [
    {
      "id": "arch-1",
      "type": "arch",
      "task": "Design sensitivity API",
      "status": "complete",
      "started": "2025-12-27T10:30:00Z",
      "completed": "2025-12-27T10:32:00Z",
      "result_summary": "3 methods proposed: bootstrap, delta, MCMC",
      "context_tokens": 1500
    },
    {
      "id": "code-1",
      "type": "code",
      "task": "Implement primary method",
      "status": "in_progress",
      "started": "2025-12-27T10:32:00Z",
      "progress": 60,
      "context_tokens": 3200
    }
  ],
  "completed_work": [
    {
      "task": "Architecture design",
      "outcome": "3 methods proposed",
      "files": ["R/sensitivity.R"]
    }
  ],
  "pending_tasks": [
    "Complete code-1 implementation",
    "Add unit tests",
    "Update documentation"
  ],
  "decisions_made": [
    {
      "decision": "Use bootstrap for confidence intervals",
      "rationale": "Best balance of accuracy and performance",
      "timestamp": "2025-12-27T10:31:00Z"
    }
  ],
  "context_usage": {
    "estimated_tokens": 25000,
    "percentage": 20,
    "last_compression": null
  },
  "errors": []
}

Read the full file on GitHub · 292 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. yesterday First seen · 292 lines · 50 tokens per session scan A ac599e9c82e6

Subscribe to this mod's changes

session-state is a skill published in the GitHub repository Data-Wise/craft (4 stars, last pushed 16d ago), licensed MIT. It adds 50 tokens to every session and 1,876 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

github-release-management

Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.

aegntic/cldcde · 27 tokens

sparc-methodology

SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.

aegntic/cldcde · 29 tokens

compound-engineering

Orchestration layer that coordinates Debt-Sentinel, Red Team Tribunal, and Spec-Lock into unified workflows. Use when you need comprehensive quality assurance with multiple validation stages. Provides safe-edit workflows, CI pipelines, enhancement pipelines, and engineering metrics dashboard.

aegntic/cldcde · 54 tokens

github-actions-workflow

Scaffolds or audits a GitHub Actions CI/CD workflow for a project. Covers job structure, caching, secrets handling, concurrency groups, environment gates, and reusable workflows via workflowcall. Invoked when the user asks to set up CI, add a GitHub Actions workflow, improve pipeline performance, or share workflow…

soulcodex/agentic · 72 tokens

code-review

Orchestrates code review by detecting the project language and architecture, then routing to the appropriate specialized review skill (code-review-go, code-review-typescript, code-review-python, code-review-php, code-review-architecture). Falls back to the generic checklist when no specific skill applies. Invoked when…

soulcodex/agentic · 80 tokens

new-gh-issue-orchestration

Orchestrates a GitHub-issue-driven delivery workflow from issue intake to PR creation using reviewer-first then worker execution. Invoked when the user provides a GitHub issue link/number and asks to start end-to-end delivery.

soulcodex/agentic · 54 tokens