{"repo":"NousResearch/hermes-agent","public_id":"9534","display_label":"Hermes agent rule enforcement and pre-action hooks","summary":"These issues and PRs concern the Hermes agent's unreliable adherence to system-prompt rules (especially under recency bias), and requests or attempts to add code-level enforcement mechanisms such as PreToolUse hooks and pre-response validation rather than relying solely on prompt instructions.","subsystem":"agent","counts":{"members":11,"open_issues":5,"open_issues_distinct":5,"open_prs":0,"closed_issues":6,"merged_prs":0,"attempt_prs":0},"landed_fix":null,"resolution":{"state":"unresolved","by":null},"freshness":{"state":"never_verified","last_verified_at":null,"is_stale":false},"grouping":{"backbone":"LLM_ONLY","link_density":0.09163636363636364},"fix_edges":[],"members":[{"kind":"issue","number":9534,"title":"Feature Request: Support for Pre-Action / Interceptor Hooks in Agent Lifecycle","url":null,"state":"closed"},{"kind":"issue","number":22956,"title":"Feature request: Pre-response validation hook for capability claims","url":null,"state":"closed"},{"kind":"issue","number":26742,"title":"[Feature]: First-Class Claim Verification & Audit Mechanism for Hermes Agent","url":null,"state":"open"},{"kind":"issue","number":32682,"title":"Skill triggering is purely prompt-driven with no code-level enforcement","url":null,"state":"open"},{"kind":"issue","number":40662,"title":"[Feature] PreToolUse enforcement hook — LLM doesn't follow system-prompt/memory rules under recency bias during debugging","url":null,"state":"open"},{"kind":"issue","number":47446,"title":"title: \"Feature Request: Agent-level pre-response hook for enforcing meta-workflow checks (e.g. skill pre-loading)\" labels: [\"enhancement\", \"agent-core\"]","url":null,"state":"closed"},{"kind":"issue","number":49764,"title":"[Bug]: Hermes Agent fails to follow rules in memory and skills","url":null,"state":"open"},{"kind":"issue","number":60429,"title":"[Bug]: hermes  agent keeps violating rules","url":null,"state":"closed"},{"kind":"issue","number":63278,"title":"Hermes is forgetful?!","url":null,"state":"closed"},{"kind":"issue","number":63770,"title":"[Feature] PreToolUse enforcement hook — prompt-level rules unreliable under recency bias","url":null,"state":"closed"},{"kind":"issue","number":68126,"title":"Framework limitation: agent cannot internalize repeated corrections — needs forced pre-action guardrails, not just system prompt rules","url":null,"state":"open"}],"trust":{"default_tier":"verified","includes_suggested":false}}