Menu
Use when archiving several workspace artifacts at once with per-artifact approval gates before any archive move executes.
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
| name | batch-archival |
| description | Use when archiving several workspace artifacts at once with per-artifact approval gates before any archive move executes. |
| status | active |
| version | 1 |
This skill also ships inside the Sovereign Ecosystem template.
Purpose: Move completed work into your archive in batches without losing anything and without moving anything the operator did not approve. The scan proposes. The operator approves. Only then do files move.
Trigger: a batch archival request, a sweep of completed plans or stale notes, or any cleanup that would relocate multiple files to your archive at once.
Inputs:
Outputs:
Terminal status is the eligibility signal. A file moves to the archive because its lifecycle ended, not because it looks old.
status: implemented for plans, status: complete for non-plan artifacts, plus any object-specific terminal status your system defines (for example retired for quest-style notes).status: draft, status: proposed, status: approved and status: ready-for-execution unless the operator explicitly approves an exception. Those statuses mean the work is still alive.completed from retired, preserve the distinction in the metadata even when both land in a shared archive folder. Avoid splitting archive folders by terminal status unless a review workflow explicitly benefits from it.Before proposing a move, check that the move will land clean:
The readiness audit is proposal and prep work only. No moves and no status changes come out of it.
Some material becomes archive-eligible on a clock rather than a status change: transcripts and session notes after a holding period, for example. Include a proposal-only audit for these. The audit proposes candidates. Nothing moves and no status changes without operator approval.
Dispatch the cheapest model that does the job well. Before each delegated step, ask whether a smaller model would produce equivalent output.
| Work type | Model |
|---|---|
| Status scans, file inventory, metadata reads | Haiku |
| Classification, readiness audit, approval-list drafting | Sonnet |
| Judgment calls on ambiguous lifecycle state | Opus |
Set the model explicitly on every subagent dispatch. Never silently inherit the top tier.
Session Closeout is where archival candidates usually surface. A close that marks a plan implemented queues it for the next batch sweep.
Pending Plan Implementation produces the implemented plans that this skill eventually carries to the archive.
If Session Closeout isn't installed yet: Install Session Closeout via Infinite Game OS. If Pending Plan Implementation isn't installed yet: Install Pending Plan Implementation via Infinite Game OS.
(Empty. Populated when execution mistakes occur during sessions.)
Use when a long-form manuscript (book chapter, ebook, multi-chapter playbook, long-form digital product) needs an editing pass to identify and remove AI writing tells. Sweeps across 8 pattern categories, assembles a structured edit packet for operator review, and applies approved edits.
Use when you have spare capacity and want to set your system improving without active attention. Operator-invoked only, never scheduled. Safe, additive, reversible hygiene work runs under a threshold model with a permanent floor of actions the agent never takes on its own.
Use when deciding whether a piece of deterministic, no-judgment work should route to a secondary AI provider instead of your primary interface. Covers the provider catalog, the five-condition eligibility test and the dispatch script.
Retire a stalled or indefinitely-deferred plan without losing its value. Candidate scan, harvest, distribute, sweep, archive and codify.
Automated pull request review for your repos. Five parallel agents, confidence scoring, convention-file compliance, and GitHub comment posting.
Use when the operator wants parallel sub-agent research aggregated into a structured report. Spawns up to 4 independent workers each investigating a different angle, then synthesizes findings for operator review. Research feeds decisions, does not trigger execution.