quantumbitcz/forge-resume
skills/forge-resume/SKILL.md
Resume a previously aborted or failed pipeline run from its last checkpoint. Use when a pipeline was interrupted, aborted with /forge-abort, or failed due to a transient error. Repairs state if needed, then continues from the last successful stage.
testing
Updated Apr 16, 2026
$ install --global
skillsauthnpx skillsauth add quantumbitcz/dev-pipeline forge-resumeInstall 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 16, 2026, 4:46 AM41.8s1 file scanned
SKILL.md
- name:
- forge-resume
- description:
- Resume a previously aborted or failed pipeline run from its last checkpoint. Use when a pipeline was interrupted, aborted with /forge-abort, or failed due to a transient error. Repairs state if needed, then continues from the last successful stage.
- allowed-tools:
- ['Read', 'Write', 'Bash', 'Agent', 'AskUserQuestion', 'TaskCreate', 'TaskUpdate']
- ui:
- { ask: true }
Prerequisites
- Check
.forge/state.jsonexists. If not: "No pipeline state found. Run /forge-run to start a new pipeline." STOP. - Read
story_state. Must beABORTEDorESCALATED. IfCOMPLETE: "Pipeline already completed. Run /forge-run for a new pipeline." If other state: "Pipeline appears to be running (state: {story_state}). Use /forge-abort first."
Instructions
-
State health check: Run the same checks as
/forge-repair-state: a. Validate JSON structure b. Check counter consistency c. Verify_seqfield d. If state is corrupted: attempt WAL recovery, report result -
Determine resume point: a. Read
previous_statefield from state.json (set by the state machine during ABORTED/ESCALATED transition — contains the state the pipeline was in before abort) b. Ifprevious_stateis empty, fall back to last successful checkpoint fromstage_timestampsc. Resume stage = the stage corresponding toprevious_stateor last successful checkpoint -
Present resume plan to user: "Pipeline was at {previous_state}. Resume options: (1) Continue from {previous_state} (recommended) (2) Go back to PLANNING (re-plan with current context) (3) Start fresh (/forge-reset + /forge-run)"
-
Resume execution: a. Set
story_stateto chosen resume point b. Release ABORTED/ESCALATED status c. Dispatch orchestrator with--from={resume_stage}d. All existing counters, scores, and findings are preserved
Edge Cases
- If worktree was deleted between abort and resume: re-create worktree from branch
- If branch was deleted: "Cannot resume -- branch {branch_name} no longer exists. Start fresh."
- If state.json was manually edited: validate with schema before resuming
Error Handling
| Condition | Action |
|-----------|--------|
| Prerequisites fail | Report specific error message and STOP |
| state.json missing | Report "No pipeline state found. Run /forge-run to start a new pipeline." and STOP |
| Pipeline still running (not ABORTED/ESCALATED) | Report "Pipeline appears to be running (state: {story_state}). Use /forge-abort first." and STOP |
| Pipeline already COMPLETE | Report "Pipeline already completed. Run /forge-run for a new pipeline." and STOP |
| state.json corrupted | Attempt WAL recovery. If recovery fails, suggest /forge-reset |
| Branch deleted between abort and resume | Report "Cannot resume -- branch no longer exists. Start fresh with /forge-run." and STOP |
| Worktree missing | Re-create worktree from branch automatically |
| Orchestrator dispatch fails | Report error. Suggest /forge-diagnose to check state health |
| State corruption | Attempt repair inline, or suggest /forge-repair-state before retrying |
See Also
/forge-abort-- Stop an active pipeline gracefully (creates the state that /forge-resume resumes from)/forge-reset-- Clear all state and start fresh (more destructive than resume)/forge-diagnose-- Read-only diagnostic before deciding whether to resume or reset/forge-repair-state-- Fix specific state.json issues before attempting resume/forge-status-- Check current pipeline state before resuming
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