can1357 51ce5a87f9 feat(prompt): standardized tool instruction and communication flow ...

- Optimized instruction sets for core agent tools including task, lsp, job, and irc.
- Standardized tool documentation structure by replacing parameter listings with structural instruction blocks.
- Mandated new communication and technical workflows for subagent results, symbol-aware code intelligence, and background task management.
- Refined messaging and coordination guidelines to prioritize inter-agent communication and direct operations.

2026-06-29 06:51:13 +02:00

..

advisor

feat(coding-agent): enabled project context injection for advisor prompts

2026-06-27 06:34:42 +02:00

agents

feat(coding-agent/task): updated assistant review prompt and export renderer

2026-06-28 07:27:02 +02:00

goals

fix: address todo reminder review feedback

2026-06-28 12:03:06 -04:00

memories

feat(coding-agent): support the local memory backend in the learn tool

2026-06-14 12:03:13 +09:00

steering

perf(coding-agent): stabilized steering message wrapping across turns

2026-06-19 06:58:06 +02:00

system

fix(agent): kept autolearn memory prompts cache-stable

2026-06-28 18:10:57 +00:00

tools

feat(prompt): standardized tool instruction and communication flow

2026-06-29 06:51:13 +02:00

bench.md

feat(prompt): standardized tool instruction and communication flow

2026-06-29 06:51:13 +02:00

ci-green-request.md

docs(prompts): standardized RFC keywords across prompt surface

2026-06-10 02:07:30 +02:00

dry-balance-bench.md

feat(dry-balance): added live bench mode for OAuth accounts

2026-06-05 11:41:07 +02:00

review-custom-request.md

feat(coding-agent): reworked subagent yields for incremental results

2026-06-28 07:27:01 +02:00

review-headless-request.md

prompts: undo experiment, update system

2026-06-04 17:41:10 +02:00

review-request.md

feat(coding-agent): reworked subagent yields for incremental results

2026-06-28 07:27:01 +02:00