ralph-abort
Abort a running agent loop and optionally revert changes
- License 许可
- MIT
- 所属仓库
- jmagly/aiwg
- 最近更新
- 2026-11-12
- Stars
- ★ 229
- Forks
- 36
01 前言 Front Matter
- name
- ralph-abort
- namespace
- aiwg
- platforms
- [ "all" ]
- commandHint
- { "model": "haiku", "category": "automation", "modelRole": "efficiency", "modelTier": "economy", "allowedTools": "Read, Write, Bash", "argumentHint": "[--keep-changes] [--revert] [--force --interactive --guidance \"text\"]" }
- description
- Abort a running agent loop and optionally revert changes
02 资源文件 1
- 参考文档references/details.md2.3 KB
03 SKILL.md 正文
Al Abort
Abort a running or paused agent loop.
HITL authorization checkpoints
Before any confirmation below, read and apply
agent-loop authorization checkpoints.
Call aiwg config authorization check --action-file "$ACTION_FILE" --target "$TARGET_REPO"
for host-classified effects. Only auto-authorized with a signed receipt skips
that workflow prompt; retain existing prompts/refusals otherwise. Platform
prompts are never bypassed. Limits, regression and threat overrides still require review.
Usage
/ralph-abort # Abort, keep changes
/ralph-abort --revert # Abort and revert all changes
/ralph-abort --force # Abort even if no active loop
Parameters
--keep-changes (default)
Stop the loop but keep all file changes made during iterations.
--revert
Revert all changes made during the agent loop using git:
- Identify commits made during loop (prefix:
ralph: iteration) - Reset to commit before loop started
- Warning: This discards work
--force
Abort even if state indicates no active loop (for cleanup).
Your Actions
Standard Abort
- Read
.aiwg/ralph/current-loop.json - Verify there's an active loop
- Mark loop as aborted
- Generate partial completion report
- Confirm to user
Output:
Agent Loop: ABORTED
Task: {task}
Iterations completed: {N}
Duration: {time}
Changes have been kept. To revert:
git reset --hard HEAD~{N}
Partial report: .aiwg/ralph/completion-{timestamp}.md
With --revert
- Read loop state
- Find all
ralph: iterationcommits from this loop - Confirm with user before reverting
- Reset git to pre-loop state
- Clean up state files
Confirmation prompt:
This will revert {N} commits:
- ralph: iteration 1 - initial attempt
- ralph: iteration 2 - fixed auth
- ralph: iteration 3 - in progress
Files to be reverted:
- src/auth.ts
- test/auth.test.ts
Type 'yes' to confirm revert:
After revert:
Agent Loop: ABORTED + REVERTED
Reverted {N} commits.
Working directory restored to pre-loop state.
State cleaned: .aiwg/ralph/current-loop.json archived
Error Handling
No active loop:
No active agent loop to abort.
Use --force to clean up stale state files if needed.
Git not available:
Git not available for --revert option.
Loop aborted, but changes cannot be reverted automatically.
Manual cleanup may be needed.
Dirty working directory (for --revert):
Cannot revert: uncommitted changes exist.
Options:
1. Commit or stash changes first
2. Use /ralph-abort without --revert to keep current state
State Changes
After abort:
current-loop.jsonmarked withstatus: "aborted"active: false- Completion report generated with partial results
- Loop can no longer be resumed
Related
/ralph-status- Check loop status before aborting/ralph-resume- Continue instead of abort
References
- @$AIWG_ROOT/agentic/code/addons/agent-loop/README.md — Ralph addon overview and loop executor documentation
- @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/human-authorization.md — Authorization rules for irreversible actions like revert
- @$AIWG_ROOT/docs/cli-reference.md — CLI reference for ralph-abort and related commands
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/README.md — SDLC framework context
04 同仓库更多 Skills
host-hardening
Read-only system hardening baseline and plan-first host hardening recommendations for SSH, Docker bind addresses, firewall persistence, datastores, exporters and audit retention.
exposure-analysis
Read-only firewall analysis and effective host exposure reconstruction for Docker published ports, UFW bypass, stale rules, CDN scope, IPv6 asymmetry and external probe allowlists.
host-hardening
Read-only system hardening baseline and plan-first host hardening recommendations for SSH, Docker bind addresses, firewall persistence, datastores, exporters and audit retention.
exposure-analysis
Read-only firewall analysis and effective host exposure reconstruction for Docker published ports, UFW bypass, stale rules, CDN scope, IPv6 asymmetry and external probe allowlists.
fixture-skill
Exercise rule delivery.
pi-local
Pi-local duplicate-precedence fixture.