session-continuation

session-continuation is a skill for Claude Code, Codex from nguyenthienthanh/aura-frog. It costs 22 tokens per session (428 once invoked), scanned A, original, MIT.

A workflow tool for saving and restoring progress across coding sessions. It records the current phase, completed work, decisions, participating agents, and other handoff details.

In plain words
What is it for?
Use it to save a handoff, resume a workflow by its identifier, or restore work from a backup when saved state is damaged.
Why use it?
It prevents long-running work from losing its context when a session ends or needs to continue later.

Skill for Claude CodeCodex

Part of the aura-frog plugin — 43 skills, 24 commands, 15 agents, 10 hooks, 6 MCP servers shipped together

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/nguyenthienthanh/aura-frog/session-continuation
Any agent
npx skills add nguyenthienthanh/aura-frog --skill session-continuation
Clone the repo
git clone --depth 1 https://github.com/nguyenthienthanh/aura-frog

Made for: Claude Code, Codex.

Or install aura-frog, the plugin that ships this one along with the rest of its 43 skills, 24 commands, 15 agents, 10 hooks, 6 MCP servers.

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-continuation

README.md
[![agentmods](https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/session-continuation.svg)](https://agentmods.dev/skills/nguyenthienthanh/aura-frog/session-continuation)
Your own site
<a href="https://agentmods.dev/skills/nguyenthienthanh/aura-frog/session-continuation"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/session-continuation.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 428 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 5.1 $0.00022 $0.00428
Opus 5 $0.00011 $0.00214
Sonnet 5 $0.00004 $0.00086
Haiku 4.5 $0.00002 $0.00043

Measured 2d ago against content hash e44ec5367bf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

session-continuation 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.

aura-frog/skills/session-continuation/SKILL.md · 62 lines

What it actually says

AI-consumed reference. Optimized for Claude to read during execution. Human-readable explanation: see docs/architecture/HIERARCHICAL_PLANNING.md or docs/getting-started/ depending on topic.

Session Continuation

Manage workflow state across sessions.

Triggers

Token ≥75% → suggest handoff. User says handoff/save → execute. User says resume + ID → load.

Handoff Flow

  1. Save to .claude/logs/runs/[id]/run-state.json: workflow_id, status, current_phase, agents, phases_completed (with deliverables), key decisions, token_usage
  2. Output: workflow ID, phase progress, deliverables, resume command

Resume Flow

  1. Load state file → validate exists/valid
  2. Restore: project context, agents, phase rules, decisions
  3. Show summary → continue from saved phase

Auto-Save

Phase completion, every 5 min, token milestones (100K/150K/175K). Silent except warning thresholds.

TOON State Format (~160 tokens vs JSON ~600)

workflow:
  id: AUTH-1234
  phase: 3
  status: in_progress
agents[2]: architect,tester

Error Handling

Not found → show available, suggest /run. Corrupted → restore from .backup.json.

Cleanup

Completed: 30 days. Cancelled: 7 days. Paused: indefinitely.

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 · 62 lines · 22 tokens per session scan A e44ec5367bf6

Subscribe to this mod's changes

session-continuation is a skill published in the GitHub repository nguyenthienthanh/aura-frog (24 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 428 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 2026-09-03.