afc-checkpoint
Save session state for later resumption
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Menü
Save session state for later resumption
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | afc:checkpoint |
| description | Save session state for later resumption |
| argument-hint | [checkpoint message] |
| model | sonnet |
| allowed-tools | ["Read","Write","Glob","Bash"] |
Saves the current work state to .claude/afc/memory/checkpoint.md. Preserves progress even if the session is interrupted.
$ARGUMENTS — (optional) checkpoint message (e.g., "Phase 2 complete, before starting UI implementation")!git rev-parse --abbrev-ref HEAD 2>/dev/null || echo "[NO_BRANCH]"
!git log --oneline -1 2>/dev/null || echo "[NO_COMMITS]"
!ls .claude/afc/specs/ 2>/dev/null || echo "[NO_SPECS]"
Collect automatically (use pre-fetched state above when available):
git status --short).claude/afc/specs/[x]/[ ] items$ARGUMENTS messagegit diff --name-only)Overwrite .claude/afc/memory/checkpoint.md (keep only the latest state):
# Session Checkpoint
> Saved: {YYYY-MM-DD HH:mm}
> Branch: {branch name}
> Commit: {hash} — {message}
## Message
{$ARGUMENTS or "automatic checkpoint"}
## Active Features
| Feature | Status | Progress |
|---------|--------|----------|
| {name} | {spec/plan/implementing/done} | {N/M tasks} |
## Incomplete Work
{concrete next steps}
## Changed Files
```
{git status --short output}
```
## Context Notes
{things to remember about the current work}
Checkpoint saved
├─ Time: {HH:mm}
├─ Branch: {branch name}
├─ Active features: {count}
├─ Progress: {completed tasks}/{total tasks}
└─ Restore: /afc:resume
Code and component analysis — analyze code, trace flows, audit consistency, inspect components
Architecture analysis and design review
Full auto pipeline — run spec-to-clean cycle automatically for new features
Resolve spec ambiguities with clarifying questions
Pipeline artifact cleanup and codebase hygiene
Expert consultation — backend, infra, PM, design, marketing, legal, or tech guidance