infinitegameos

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 archiving several workspace artifacts at once with per-artifact approval gates before any archive move executes.

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.

Use when wrapping up a session that made commits or governance changes. A fast three-action close: breadcrumb what you touched, refresh your handoff note, commit with a readable body.

Use to run a post-job relationship cadence. Four touchpoints: +24-48h thank-you, +14d referral ask, +90d maintenance check-in, +180d re-engagement. Customer notes live as Obsidian YAML frontmatter. A single Dataview query surfaces who is due for outreach. CRM-lite that covers a solo service business up to ~50 customers.

Run a full multi-lens team meeting across all active jackets. Twelve-step flow from convene through close. The operator chairs, the knowledge-design lens synthesizes, each jacket prepares its perspective independently, and the session closes with a structured decision record.

Run a 1:1 (or two-lens) advisory session with a named AI advisor jacket. Loads jacket context, runs the universal session flow with the Three Solutions Rule and Challenge and Illumination active, and closes with a structured capture.

Execute an approved plan (or approved subset) using the plan note as the implementation context, breadcrumb record and outcome summary.

Adversarial pre-build pass that challenges a plan before execution begins. Five angles, one verdict.

Use when you need to scrape pages, extract structured data or interact with web interfaces via headless browser automation without using screenshots.

Use when an AI interface hits an error mid-task and should diagnose, fix and continue autonomously without stopping for every recoverable mistake.

Build new skills autonomously. Interview the operator about the skill's intent, research relevant patterns and protocols, write a complete SKILL.md to the canonical location.

Use when encountering any bug, unexpected behavior, test failure or system malfunction before proposing fixes. Use especially when under time pressure or when quick fixes have already failed.