quantumbitcz/forge-abort
skills/forge-abort/SKILL.md
[writes] Stop an active pipeline run gracefully. Use when you want to pause work, need to change approach mid-pipeline, or want to interrupt a long-running run. Preserves state for /forge-recover resume. Safer than /forge-recover reset which clears all state.
devops
Updated Apr 18, 2026
$ install --global
skillsauthnpx skillsauth add quantumbitcz/dev-pipeline forge-abortInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 18, 2026, 5:38 AM48.9s1 file scanned
SKILL.md
- name:
- forge-abort
- description:
- [writes] Stop an active pipeline run gracefully. Use when you want to pause work, need to change approach mid-pipeline, or want to interrupt a long-running run. Preserves state for /forge-recover resume. Safer than /forge-recover reset which clears all state.
- allowed-tools:
- ['Read', 'Bash', 'AskUserQuestion']
- ui:
- { ask: true }
Flags
- --help: print usage and exit 0
- --dry-run: preview actions without writing
Exit codes
See shared/skill-contract.md for the standard exit-code table.
Prerequisites
- Check
.forge/state.jsonexists. If not: "No active pipeline to abort." STOP. - Read
story_statefrom state.json. IfCOMPLETEorABORTED: "Pipeline already finished (state: {story_state})." STOP.
Instructions
- Read current state:
story_state,convergence.phase,total_iterations - Confirm with user via AskUserQuestion:
"Pipeline is at stage {story_state}, iteration {total_iterations}. How would you like to proceed?"
- Option 1: "Abort and preserve state for resume"
- Option 2: "Abort and reset (equivalent to /forge-recover reset)"
- Option 3: "Cancel — keep running"
- If option 1 (preserve):
a. Transition to ABORTED via the state machine:
bash shared/forge-state.sh transition user_abort_direct --forge-dir .forgeb. Release.forge/.lockif held:rm -f .forge/.lockc. Do NOT delete worktree (preserves work for resume) d. Report: "Pipeline aborted at {stage}. State preserved. Run /forge-recover resume to continue." - If option 2 (reset): Delegate to
/forge-recover reset - If option 3 (cancel): "Abort cancelled. Pipeline continues."
Important: Never write directly to state.json. Always use forge-state.sh transition to maintain state machine integrity.
Post-Abort State
story_state: ABORTEDprevious_state: preserved for /forge-recover resume- All counters preserved
- Worktree preserved
- Lock released
Error Handling
| Condition | Action |
|-----------|--------|
| Prerequisites fail | Report specific error message and STOP |
| state.json missing | Report "No active pipeline to abort." and STOP |
| Pipeline already finished | Report "Pipeline already finished (state: {story_state})." and STOP |
| State transition fails | Report "Could not transition to ABORTED state. State machine error: {error}." Suggest /forge-recover repair |
| Lock file removal fails | Log WARNING. Lock file will be detected as stale on next run |
| state.json write fails | Report error. State may be partially updated. Suggest /forge-recover repair |
| State corruption | Attempt abort anyway via state machine. If that fails, suggest /forge-recover reset |
See Also
/forge-recover resume-- Resume the aborted pipeline from where it stopped/forge-recover reset-- Clear all state (more destructive -- use when resume is not needed)/forge-status-- Check pipeline state before deciding to abort/forge-recover rollback-- Rollback code changes made before the abort
Related Skills
quantumbitcz/forge
development
VerifiedTrustedCommunity
[writes] Build, fix, deploy, review, or modify code in this project. Universal entry for the forge pipeline. Auto-bootstraps on first run; brainstorms before planning when given a feature description. Use when you want to take any productive action: implementing features, fixing bugs, reviewing branches, deploying, committing, running migrations.
SKILL.mdUpdated Apr 30, 2026
quantumbitcz/forge-admin
tools
VerifiedTrustedCommunity
[writes] Manage forge state and configuration: recovery, abort, config edits, session handoff, automations, playbooks, output compression, knowledge graph maintenance. Use when you need to recover from broken pipeline state, edit settings, or manage long-lived state.
SKILL.mdUpdated Apr 30, 2026
quantumbitcz/forge-handoff
development
VerifiedTrustedCommunity
[writes] Create, list, show, resume, or search forge session handoffs. Use when context is getting heavy and you want to transfer a forge run or conversation into a fresh Claude Code session, or to resume from a prior handoff artefact. Subcommands - no args (write), list, show, resume, search.
SKILL.mdUpdated Apr 23, 2026
quantumbitcz/forge-graph
development
VerifiedTrustedCommunity
[writes] Manage the Neo4j knowledge graph. Subcommands: init, rebuild (writes); status, query <cypher>, debug (read-only). Requires Docker. No default — an explicit subcommand is required. Use when setting up the graph for the first time, rebuilding after major refactors, checking graph health, or running ad-hoc Cypher diagnostics.
SKILL.mdUpdated Apr 21, 2026