Menu
Preview a LAEE action plan — classify risk, check undo availability, inspect credential touchpoints — without executing anything.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Verify a feature spec, plan, or PR against the non-negotiable principles in `.specify/memory/constitution.md`.
Extract session insights after a task completes and feed them into Morphic's self-evolution engine. Captures what worked, what didn't, and proposes prompt/routing tweaks.
Keep CLAUDE.md (thin router) and AGENTS.md (telegraph-style) in sync. Detects drift in command lists, paths, and routing tables between the two root instruction files.
Generate a monthly or on-demand cost report across LLM providers, local LLMs, and agent engines. Flags overspend and suggests downgrades.
Run live end-to-end verification across Morphic-Agent's 6 agent CLI engines. Produces a baseline comparison table with duration and cost per engine.
Inspect Morphic-Agent's fractal task graph for a given task_id. Reports bypass classifier decisions, Gate 2 skips, parallelism, and regression flags.
| name | laee-dry-run |
| description | Preview a LAEE action plan — classify risk, check undo availability, inspect credential touchpoints — without executing anything. |
| when_to_use | Before approving a batch of LAEE actions in full-auto mode, or when the user wants to understand what would happen if they said yes. |
| argument-hint | [plan-id | inline action list] |
| allowed-tools | ["Read","Grep","Glob"] |
| model | sonnet |
You simulate a LAEE plan's execution without side effects. Hands-off preview.
Either:
ActionPlan in .morphic/plans/<id>.json.$ARGUMENTS.domain/services/risk_assessor.py logic (read only).LOCAL_TOOLS risk level — flag mismatches.~/.ssh/*, ~/.aws/*, .env*, id_rsa*, *.pem.reversible flag + undo_hint).LAEE_APPROVAL_MODE (from .claude/settings.json env).local-safety-gate subagent.# LAEE Dry Run — <plan_id>
## Mode
- Current: confirm-destructive (from settings.json)
## Actions
| # | Tool | Risk | Approval | Reversible | Credential? |
|---|---|---|---|---|---|
| 1 | shell_exec | MEDIUM | auto | yes | no |
| 2 | fs_delete | HIGH | prompt | YES (trash) | no |
| 3 | dev_git | MEDIUM | auto | no | no |
## Summary
- 3 actions
- 1 will prompt user (HIGH)
- 0 credential touchpoints
- All reversible except #3
## Verdict
SAFE_TO_PROCEED / NEEDS_REVIEW / BLOCK
## Risk breakdown
- SAFE: 0 | LOW: 0 | MEDIUM: 2 | HIGH: 1 | CRITICAL: 0