Results for “token-compression”

Generates at most one token recommendation and one prediction-market pick per run, each with a falsifiable thesis, entry, sizing, and kill criterion. Returns NO_PICK when no candidate meets the bar.

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

Compress an oversized SKILL.md to under 200 lines without losing effectiveness. Load when a skill exceeds 200 lines, when AGENTS.md triggers compression after a skill edit, or when the user asks to compress, shrink, slim down, or optimize a skill. Also triggers on "this skill is too long", "reduce skill size", "make this skill shorter". Applies to all skills including meta skills — the 200-line rule has no exceptions. Preserves hard gates, gotchas, output format, routing triggers, and at least one example. When genuinely CORE content cannot be compressed away, invokes split-skill instead of degrading the skill.

info-to-ink

崔健（摇滚）认知与表达框架（压缩蒸馏）：地下与现场感、隐喻与直白并置… 触发：一块红布 等。非煽动违法

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

The central pattern.

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Reduces token usage by ~75% by stripping filler words, articles, and pleasantries while preserving full technical accuracy. Activates on user commands like 'caveman mode' or 'be brief'.

Compresses images to WebP (default) or PNG with automatic tool selection, reducing file size while preserving quality.

哆啦A梦（子供向）认知与表达框架（压缩蒸馏）：道具脑洞、大雄成长线、温柔科幻 触发：机器猫 等。勿逐字抄录版权对白

Compresses images to WebP (default) or PNG with automatic tool selection. Use when user asks to "compress image", "optimize image", "convert to webp", or reduce image file size.

BISON v2.0 — Conviction Holder (Hardened). Top 10 assets by volume. All signals are score contributors — no hard gates. Scanner enters via create_position internally (Wolverine pattern). RatchetStop exits. Thesis exit REMOVED. v2.0: every hard gate converted to score contributor, ensureExecutionAsTaker=false, conviction-scaled margin 25-37%.

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

Token Standards

Use for UI/UX and design-system work when Codex should convert visual direction or existing UI into reusable design tokens.

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

<!-- IJFW: narration-not-applicable -->

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

Builds a local knowledge graph of a codebase using tree-sitter and graph algorithms, then answers architecture questions by querying the graph instead of reading many files, saving tokens.

建议在逻辑间隔处手动压缩上下文，以在任务阶段中保留上下文，而非任意的自动压缩。

Extends effective context capacity through strategic compression, masking, caching, and partitioning techniques.