sorratheorc/planall
skill/planall/SKILL.md
Automated batch planning for intake_complete work items. Discovers all items in intake_complete status and invokes /plan for each sequentially, producing a summary report.
testing
Updated Jun 13, 2026
$ install --global
skillsauthnpx skillsauth add sorratheorc/sorraagents planallInstall 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: Jun 13, 2026, 5:01 AM86.1s6 files scanned
SKILL.md
- name:
- planall
- description:
- Automated batch planning for intake_complete work items. Discovers all items in intake_complete status and invokes /plan for each sequentially, producing a summary report.
PlanAll
Use this skill when asked to run batch planning on all intake_complete work items. It processes each item sequentially, detects items requiring producer input, and provides a summary report.
Behavior
- Query
wl list --stage intake_complete --jsonto discover all eligible work items - For each item, claim it (
wl update <id> --status in_progress) and invoke/plan - Detect items needing producer input (unanswered questions, non-zero exit, or specific output patterns)
- Continue processing remaining items even when one requires input or encounters an error
- Produce a summary report showing totals and per-item outcomes
Command invocation
PlanAll can be invoked in the following ways:
/skill:planall— Process all intake_complete items with markdown summary output/skill:planall --json— JSON output for programmatic consumption/skill:planall --parent-id <id>— Post the summary as a comment on the specified parent work itempython3 skill/planall/scripts/planall.py— Direct Python invocationpi run /planall— Agent framework invocation
Output
After processing all items, PlanAll produces a summary report:
# PlanAll Summary
**Total processed**: 5
**Planned**: 3
**Needs input**: 1
**Errors**: 1
## Results
- **SA-ITEM-001**: `planned`
- **SA-ITEM-002**: `planned`
- **SA-ITEM-003**: `needs_input`
- **SA-ITEM-004**: `error`
- **SA-ITEM-005**: `planned`
When --json is used, the output is a JSON object:
{
"total": 5,
"planned": 3,
"needs_input": 1,
"errors": 1,
"items": [
{"id": "SA-ITEM-001", "title": "...", "outcome": "planned"}
]
}
Producer-input detection
PlanAll detects items requiring producer intervention by:
- Non-zero exit code from the
/plancommand - Presence of question-like patterns in the output (e.g.,
? (yes/no), "What should", "Do you want") - Any exception during the plan invocation
Items flagged as needs_input are not retried — the skill moves on to the next item.
Error handling
- If
wl listfails (non-zero exit or exception), returns an empty list gracefully - If claiming an item fails, logs a warning and marks the item as
error - If
/planfails for an item, logs a warning and continues to the next item - All errors are captured in the summary report
Idempotence
- PlanAll processes only items currently in
intake_completestage - Items that have already been planned (moved past
intake_complete) are naturally excluded on subsequent runs - Re-running PlanAll is safe and will only process remaining intake_complete items
Examples
# Process all intake_complete items
python3 skill/planall/scripts/planall.py
# JSON output
python3 skill/planall/scripts/planall.py --json
# Post summary as a comment on a parent epic
python3 skill/planall/scripts/planall.py --parent-id SA-0MQA6ECEU003GUKH
Scripts
- Canonical runner:
skill/planall/scripts/planall.py - Tests:
skill/planall/tests/test_planall.py
Related skills
command/plan.md— The/plancommand that PlanAll invokes for each itemskill/ralph/SKILL.md— Ralph orchestration loop that provides auto-planning for individual items
Related Skills
sorratheorc/git-management
data-ai
VerifiedTrustedCommunity
Unified git management skill that orchestrates the full feature-branch lifecycle — create, commit, push, PR, merge, cleanup — for both AI agents and human operators.
SKILL.mdUpdated Jun 7, 2026
sorratheorc/ship
development
VerifiedTrustedCommunity
Canonical push-to-dev and branch-policy enforcement for agents. Provides the push-to-dev workflow, branch naming, conflict handling, and release process guidance. Trigger with: /skill:ship push-to-dev
SKILL.mdUpdated Jun 2, 2026
sorratheorc/implement-single
development
VerifiedTrustedCommunity
Write tests, docs and code for a single, specific Worklog work item. Unlike the `implement` skill, this skill operates on exactly one work-item without using `wl next` for recursive dependency resolution or sub-task discovery. It is designed to be invoked by Ralph's per-child loop so that each child is implemented, audited, and remediated independently. Trigger on user queries such as: 'implement-single <work-item-id>', 'complete <work-item-id> (single)', or when Ralph delegates a single-child implement step.
SKILL.mdUpdated May 28, 2026
sorratheorc/ralph
testing
VerifiedTrustedCommunity
Run an iterative implement→audit loop for a target work item. Ralph is a launcher/orchestrator, not the normal Worklog implementation workflow.
SKILL.mdUpdated May 18, 2026