xaccefy

Quick-reference card for all sweep modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /sweep-help, "sweep help", "what sweep commands", "how do I use sweep".

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "sweep", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).

Whole-repo audit for over-engineering. Like sweep-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find bloat", "sweep-audit", or "/sweep-audit". One-shot report, does not apply fixes.

Harvest every `shortcut:` comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals sweep leaves behind get tracked instead of rotting into "later means never". Use when the user says "sweep debt", "/sweep-debt", "what did sweep defer", "list the shortcuts", "sweep ledger", or "what did we mark to do later". One-shot report, changes nothing.

Show sweep's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger: /sweep-gain, "sweep gain", "what does sweep save", "show sweep impact", "sweep scoreboard".

Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this over-engineered", "simplify review", or invokes /sweep-review. Complements correctness-focused review, this one only hunts complexity.

Full pipeline orchestration skill for vulnerability discovery. Teaches the harness agent how to run stages with state tracking, schema validation, reachability trace, gapfill, and structured reporting.

Full web application penetration testing methodology for Pi agent. Covers reconnaissance, attack classes, detection, confirmation, evasion, and reporting. Use when the agent must test a live web target within a sanctioned engagement. Replaces the removed engage tool.

Use when tracking security investigations, bug bounty findings, CTF leads, audit evidence, exploit chains, dead ends, or reports in the Casefile ledger.

Research validated sources and build well-sequenced lessons from them. Pairs with /quiz (self-check) and /test (spaced review). No Socratic grilling, no testing — those are separate commands.

Self-quiz over what /learn built — retrieval questions with immediate feedback. Run after /learn to check understanding. Lightweight; no spaced scheduling and no scoring file (that's /test).

Spaced-retrieval review over the lessons and glossary /learn built. Scores recall (known/shaky/unknown), applies spacing + interleaving, and feeds weak items back to /learn as topics for more lessons.