AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Checkpoint

skill-antifragiletech-antifragile-claude-code-checkpoint · by AntifragileTech

A Claude skill from AntifragileTech/antifragile-claude-code.

No reviews yet
0 installs
7 views
0.0% view→install

Install

$ agentstack add skill-antifragiletech-antifragile-claude-code-checkpoint

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-antifragiletech-antifragile-claude-code-checkpoint)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

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 →
Are you the author of Checkpoint? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Session Checkpoint

Write a structured progress summary for this session. This replaces the observer/memory agent pattern — same output, zero overhead, no auth failures.

Steps

  1. Gather current state by running these commands:
  • git log --oneline -10 — recent commits
  • git diff --name-only HEAD — uncommitted changed files
  • git branch --show-current — active branch
  • git status --short — working tree state
  • Check for any open TODO.md, NEXT-SESSION-PROMPT.md, or *.todo files in the project root
  1. Create the checkpoint directory if needed: ~/.claude/memory/
  2. Generate a markdown file named checkpoint-YYYY-MM-DD-HHMMSS.md in ~/.claude/memory/
  3. Populate it with the following structure — use TodoWrite list as primary source, git data as supplement:
# Checkpoint — [DATE TIME]

## Project
[Current project path] | Branch: [branch name]

## Changes Made (this session)
- [Each completed todo item with brief details]

## Files Modified
- [From git diff --name-only HEAD, grouped by app if monorepo]

## Recent Commits
- [From git log --oneline -10]

## Blockers
- [Any build failures, auth issues, unresolved errors]

## Key Decisions
- [Architectural or approach decisions made]

## Next Steps
- [Specific actionable items with file paths and line numbers where possible]

## Resume Prompt
"Continue from checkpoint [DATE]. Last work: [one-line summary]. Next: [first next step]."
  1. If no TodoWrite list exists, reconstruct from the conversation: what was asked, what was done, what's left.
  2. Print the full path to the saved checkpoint file when done.

Source & license

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

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

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.