* perf(od-next): streamline tool use and media input prompts
* fix(od-next): drop the runtime-state literal from the core tool rule
The v2.1.1 core prompt named `open-design-runtime-state` inside the
"not a tool name" bullet. In the two post-optimization eval batches the
model called that exact name as a tool in 5 of 29 deliveries (1 of 30
before the sentence existed): a negated mention raises the name's
salience right where the model is about to emit the runtime-state block.
Keep the rule, drop the literal: protocol blocks are structured text
output, not tools. Bump core asset to 2.1.2 and the bundled package to
2.0.2; orchestration is untouched and stays 2.0.1.
* fix(od-next): carry protocol output guidance into tool optimization
* fix(od-next): preserve run workspace scope in dynamic skill reads
---------
Co-authored-by: bone3deep1962-collab <bone3deep1962@gmail.com>
Co-authored-by: NJUHua <113895241+NJUHua@users.noreply.github.com>
This directory contains functional skills: capabilities the agent invokes to do work on user input, such as briefs, audits, utilities, and asset packagers. Each folder has a SKILL.md and may include assets/ or references/.
Read docs/skills-protocol.md for frontmatter, discovery, precedence, and mode semantics. Copy the closest functional skill, keep the folder self-contained, and use an explicit od.mode appropriate for work performed on user input.