restore-checkpoint

A session-restoration skill that loads a supplied checkpoint file and restores the work state it describes.

In plain words
What is it for?
Restoring sessions when the user explicitly provides a valid checkpoint artifact at the start.
Why use it?
It helps continue a previous session while checking the saved state against the current instructions for conflicts.

Skill for Claude CodeCodex

Part of the ai-context-kit plugin — 12 skills 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/msiccdev/ai-context-kit/restore-checkpoint
Any agent
npx skills add MSiccDev/ai-context-kit --skill restore-checkpoint
Clone the repo
git clone --depth 1 https://github.com/MSiccDev/ai-context-kit

Made for: Claude Code, Codex.

Or install ai-context-kit, the plugin that ships this one along with the rest of its 12 skills.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 553 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 $0.00044 $0.00553
Opus 5 $0.00022 $0.00277
Sonnet 5 $0.00009 $0.00111
Haiku 4.5 $0.00004 $0.00055

Measured 3d ago against content hash e5f09705e88e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

restore-checkpoint 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 3d 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.

skills/restore-checkpoint/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Restore Checkpoint

Purpose

Load a checkpoint artifact and restore the session state it describes, surfacing any conflicts with active instruction files before any work begins.

How to Invoke

Load or attach this file's contents into your AI session to activate the workflow (paste, upload, or reference with #file:skills/restore-checkpoint/SKILL.md in VS Code Copilot Chat). In Claude Projects, add it to project knowledge. See Invoking Skills in the README for full platform guidance.

When To Use

  • At the start of a session when the user provides a checkpoint file.
  • Do not apply checkpoint state mid-session or without the user explicitly providing the artifact.

Required Inputs

  • The checkpoint artifact file (provided by the user at session start).
  • Active instruction files (user context and project AGENTS.md) already loaded in context.

Workflow

  1. Read the checkpoint artifact and confirm it contains the checkpoint: true marker and all required schema fields per references/restore-rules.md.
  2. For each field in the checkpoint, compare it against any values defined in active instruction files.
  3. For each conflict found: surface it explicitly — state the conflicting values from both sources and which source each value comes from.
  4. Ask the user which source to apply for each conflict.
  5. Apply instruction file values as the default for any conflict the user does not respond to.
  6. Present the full resolved session state to the user for confirmation.
  7. Do not begin any task work until the user has confirmed the restored state.

Output Expectations

  • A clear confirmation summary showing all restored session state values and their sources.
  • Each conflict recorded as resolved, with the winning source noted.
  • Any missing required fields flagged, with the user asked to supply them or apply the instruction file default.

Resources

  • references/restore-rules.md for spec section 4.4.3 restore rules, conflict resolution logic, and examples.

Read the full file on GitHub · 47 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 47 lines · 44 tokens per session scan A e5f09705e88e

Subscribe to this mod's changes

restore-checkpoint is a skill published in the GitHub repository MSiccDev/ai-context-kit (12 stars, last pushed 5d ago), licensed MIT. It adds 44 tokens to every session and 553 once invoked, about $0.0002 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.