oh-my-agent 14.7.9 → 14.7.11

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (3) hide show
  1. package/README.md +1 -1
  2. package/bin/cli.js +780 -778
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -280,7 +280,7 @@ Deterministic SLM execution is therefore a separate, optional product direction
280
280
  ## Why oh-my-agent?
281
281
 
282
282
  - **Role-based** — agents modeled like a real engineering team, not a pile of prompts
283
- - **Token-efficient** — skills load in two layers, so a 5-agent session holds ~17-19K tokens of skill context on ordinary tasks instead of the 72K it would take to load every resource ([measured, with the script](https://github.com/first-fluke/oh-my-agent/blob/main/web/docs/core-concepts/skills.md#token-savings-math))
283
+ - **Conditional context** — dispatch loads the owning skill and defers supporting references until the task needs them. File-size scenarios and runtime loading are reported separately ([measurement guidance](https://github.com/first-fluke/oh-my-agent/blob/main/web/docs/core-concepts/skills.md#token-savings-math)).
284
284
  - **Recoverable** — after 2 failed retries, `orchestrate` spawns hypothesis variants in parallel and keeps the highest-scoring result instead of retrying a wrong approach forever
285
285
  - **Monorepo-aware** — `detectWorkspace` reads pnpm / nx / turbo / lerna and routes each agent to its workspace
286
286
  - **Multi-vendor** — mix Antigravity, Claude, Codex, Cursor, Kiro, and Qwen per agent type