Install
$ agentstack add skill-msiccdev-ai-context-kit-restore-checkpoint ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
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](../../README.md#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
- Read the checkpoint artifact and confirm it contains the
checkpoint: truemarker and all required schema fields perreferences/restore-rules.md. - For each field in the checkpoint, compare it against any values defined in active instruction files.
- For each conflict found: surface it explicitly — state the conflicting values from both sources and which source each value comes from.
- Ask the user which source to apply for each conflict.
- Apply instruction file values as the default for any conflict the user does not respond to.
- Present the full resolved session state to the user for confirmation.
- 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.mdfor spec section 4.4.3 restore rules, conflict resolution logic, and examples.
Constraints And Safety
- Never apply checkpoint state silently — always confirm with the user first.
- Instruction files are the default source when the user does not respond to a conflict prompt.
- If the checkpoint is missing required fields, flag them before proceeding.
- Checkpoint state is only valid when provided at session start — do not apply it mid-session.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: MSiccDev
- Source: MSiccDev/ai-context-kit
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.