Defame1297/holocron
0
0
Fork 0
Code Issues 14 Pull Requests Actions Packages Projects Releases 3 Wiki Activity

docs(agents): expand subagent guidance with parallelism and sequencing rules

Browse Source 
## Why
The original rule said "prefer subagents" but gave no guidance on when to
run them in parallel vs. sequentially, or when to invoke a relevant skill.
This closes the ambiguity so agents make correct scheduling decisions without
having to reason it out from first principles each time.
This commit is contained in:
Defame1297
2026-06-28 11:15:35 +00:00
parent 200959c167
commit a203e99b08
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
core/AGENTS.md
View File

@@ -15,7 +15,7 @@
- Reads, searches, exploration: proceed without asking. - Reads, searches, exploration: proceed without asking.
- Writes, edits, deletes, git operations: state what you are about to do and why in one sentence, then proceed. Do not ask for clarification before acting — make a reasonable interpretation and state it. Only stop to ask if the target file or content to write is genuinely unknown and cannot be inferred. - Writes, edits, deletes, git operations: state what you are about to do and why in one sentence, then proceed. Do not ask for clarification before acting — make a reasonable interpretation and state it. Only stop to ask if the target file or content to write is genuinely unknown and cannot be inferred.
- Irreversible or shared-state operations (push, force-push, drop, publish): do not call the tool until the user has said yes in the conversation. State what you are about to do, then wait for explicit approval. Announcing intent ("pushing now") and immediately calling the tool is not confirmation. - Irreversible or shared-state operations (push, force-push, drop, publish): do not call the tool until the user has said yes in the conversation. State what you are about to do, then wait for explicit approval. Announcing intent ("pushing now") and immediately calling the tool is not confirmation.
- always prefer using subagents (clean or with session context) to execute well bounded actions that require no human interaction - always prefer using subagents (clean or with session context) to execute well bounded actions that require no human interaction. subagents can be parallelized if they will not write to the same files. subagents must be run sequentially if they depend on eachothers changes or handoff, or will write to the same files. if skills are present relevant to the work of the subagent, they should invoke that skill.
# Content index # Content index