# Checkpoint

> A Claude skill from mattjaikaran/meridian.

- **Type:** Skill
- **Install:** `agentstack add skill-mattjaikaran-meridian-checkpoint`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [mattjaikaran](https://agentstack.voostack.com/s/mattjaikaran)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [mattjaikaran](https://github.com/mattjaikaran)
- **Source:** https://github.com/mattjaikaran/meridian/tree/main/skills/checkpoint

## Install

```sh
agentstack add skill-mattjaikaran-meridian-checkpoint
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# /meridian:checkpoint — Manual Save Point

Create a structured checkpoint with notes for later resume.

## Arguments
- `` — Optional notes about current state
- `--blockers ` — Record blockers

## Procedure

### Step 1: Determine Current Position
```bash
PYTHONPATH=$MERIDIAN_HOME uv run --project $MERIDIAN_HOME -- python -c "
import json
from scripts.db import connect, get_db_path
from scripts.state import compute_next_action, get_status
conn = connect(get_db_path('.'))
status = get_status(conn)
action = compute_next_action(conn)
print(json.dumps({
    'milestone_id': status['active_milestone']['id'] if status.get('active_milestone') else None,
    'phase_id': status['current_phase']['id'] if status.get('current_phase') else None,
    'action': action
}, default=str))
conn.close()
"
```

### Step 2: Gather Recent Decisions
```bash
PYTHONPATH=$MERIDIAN_HOME uv run --project $MERIDIAN_HOME -- python -c "
import json
from scripts.db import connect, get_db_path
from scripts.state import list_decisions
conn = connect(get_db_path('.'))
decisions = list_decisions(conn, limit=10)
print(json.dumps(decisions, default=str))
conn.close()
"
```

### Step 3: Create Checkpoint
```bash
PYTHONPATH=$MERIDIAN_HOME uv run --project $MERIDIAN_HOME -- python -c "
import json
from scripts.db import connect, get_db_path
from scripts.state import create_checkpoint
conn = connect(get_db_path('.'))
create_checkpoint(conn,
    trigger='manual',
    milestone_id='',
    phase_id=,
    notes='',
    blockers=,
    decisions=,
    repo_path='.'
)
conn.close()
print('Checkpoint saved.')
"
```

### Step 4: Export State
```bash
PYTHONPATH=$MERIDIAN_HOME uv run --project $MERIDIAN_HOME -- python -c "
from scripts.export import export_state
export_state('.')
print('State exported to .meridian/meridian-state.json')
"
```

### Step 5: Confirm
Print checkpoint summary with timestamp, position, and notes.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [mattjaikaran](https://github.com/mattjaikaran)
- **Source:** [mattjaikaran/meridian](https://github.com/mattjaikaran/meridian)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-mattjaikaran-meridian-checkpoint
- Seller: https://agentstack.voostack.com/s/mattjaikaran
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.