MythEclipse/asepharyana-hub-guide
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix(hooks): only fire ok:false when clearly violating principles

Browse Source 
Previously returned ok:false every time because 'fully applied' all 8
skills is impossible in one response. Now ok:true by default (silent),
only fires ok:false when Claude is clearly guessing or violating rules.
This commit is contained in:
asepharyana
2026-07-26 12:21:31 +07:00
parent eba82a9b2f
commit 7e76b2da44
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
hooks/hooks.json
+1 -1
View File
@@ -3,7 +3,7 @@
"Stop": [{
"hooks": [{
"type": "prompt",
"prompt": "Hub-guide best-practice skills are loaded. MANDATORY: engineering-principles, clean-code, clean-architecture, testing, error-handling, security, git-workflow, api-design. Never assume or guess — always find evidence in codebase or docs. If these skills are already being applied, respond: {\"ok\": true}. If not fully applied, respond: {\"ok\": false, \"reason\": \"[hub-guide] Apply MANDATORY skills: engineering-principles, clean-code, clean-architecture, testing, error-handling, security, git-workflow, api-design.\"}"
"prompt": "Check if hub-guide MANDATORY skills are being applied where relevant: engineering-principles, clean-code, clean-architecture, testing, error-handling, security, git-workflow, api-design. If the assistant is using evidence from codebase/docs instead of guessing, and is not violating any of these principles, respond: {\"ok\": true}. Only respond {\"ok\": false, \"reason\": \"[hub-guide] Apply MANDATORY skills: engineering-principles, clean-code, clean-architecture, testing, error-handling, security, git-workflow, api-design.\"} if the assistant is clearly guessing or violating these principles."
}]
}]
}