A shared vocabulary is navigation equipment — every term below is a labeled crystal the whole crew can pull off the shelf and mean the same thing by. The "first seen" column doubles as a timeline: read it top to bottom and you can watch the practice evolve.
Same word, same meaning, whole crew.
Teams that share precise terms move faster — not because jargon is clever, but because every shared term is a compressed agreement you never have to renegotiate. When someone says "clean handoff" or "no saved check, no claim", the whole crew lights up with the same shape.
Broadcast the terms until they land identically. Then stop explaining and start building.
| Term | Definition | First seen |
|---|---|---|
| Context is King | Early shorthand for making relevant evidence available to the agent. | Mar 2025 |
| Context engineering | Deliberate selection, compression, and presentation of agent evidence. | Jun 2025 |
| Scaffold → Outline → Instruct → Execute | Staged workflow separating setup, planning, prompting, implementation. | Mar 2025 |
| Forced Context | Manually curated search or file evidence supplied to the agent. | Mar 2025 |
| Three Pillars of Agent Knowledge | Personal knowledge, documentation, institutional/codebase knowledge. | Jun 2025 |
| Rule of Threes | Generate ~three options or perspectives before choosing. | Mid 2025 |
| Print mode | Non-interactive agent invocation that participates in shell composition. | Aug 2025 |
| Opus / Dopus / Popus | Historical wrappers for model choice, permission bypass, clipboard-seeded prompting. | Aug 2025 |
| Hypothesis Mode | Small, reversible try-fail-learn experimentation. | Aug 2025 |
| Compaction bail | Save the useful artifact and restart rather than continuing degraded. | Aug 2025 |
| YOLO mode | Informal name for bypassing permission checks; inherently risky. | Aug 2025 |
| Scripting 2.0 | Language-model judgment as a programmable runtime layer. | Oct 2025 |
| Diagram-Driven Development | Mermaid diagrams as persistent engineering memory. | Nov 2025 |
| Front-Stage / Back-Stage | Diagram split between user-visible behavior and supporting implementation. | Nov 2025 |
| Sandcastles | Cheap, disposable agent-built tools that must earn durability. | Nov 2025 |
| Progressive disclosure | Loading specialized instructions only when relevant. | Dec 2025 |
| Council of Five | Independent perspectives generated before a consequential decision. | Dec 2025 |
| Taste | Human judgment used to select among plausible alternatives. | Dec 2025 |
| Manager / worker | Context-rich coordinator paired with narrow execution agents. | May 2026 |
| Imp | A narrow, preloaded specialist agent or capability. | Jun 2026 |
| Browser Bridge | Bounded repo context sent through a browser model; local execution and verification. | Jun 2026 |
| Oracle | The browser-routed external model used for broad planning, critique, synthesis. | Jun 2026 |
| No saved check, no claim | Persistent external evidence required before asserting completion. | Jun 2026 |
Vocabulary is a living surface: the newest terms (2026 column) are the most likely to shift as the practice settles. When a term and a tool disagree, trust the concept — names move faster than principles.
Names move faster than principles.— when a term and a tool disagree
Sealed. Studied. Not reinstalled.
Preserved for study, not for use. Each exhibit is a hard-won directional change — something genuinely tried, that hit a wall, and got replaced. Knowing why the current gear won is what inoculates you against the next hype cycle.
| Retired | Current gear | |
|---|---|---|
| Large speculative rule libraries | → | Thin, reactive rules + progressive disclosure |
| Maximum-context dumps | → | Relevance density, preprocessing, fresh sessions |
| Unbounded agent fan-out | → | Bounded ownership; one–two supervised tracks |
| MCP everywhere | → | Mature CLIs first; MCP for real new capability |
| Trusting "done" or proprietary rewind | → | Git + saved tests, diffs, logs, screenshots |
| Model rankings as doctrine | → | Dated sidebars (see the --model stamp) |
| Permission bypass as convenience | → | Risky modes gated by isolation + verification |
| Agent prose as enforcement | → | Hooks and CI for non-negotiable invariants |
The experiments that failed — container sandboxes, sprawling councils, unattended loops — stay valuable because their failures mapped the boundaries of autonomy. They are exhibits, not doctrine.
same meaning // whole crew