# NousResearch/hermes-agent · Gating agent edits to skills behind user approval

## Open now

- 2 issues, 2 PRs open on GitHub.
- #25083: Feature: Immutable/protected skills - prevent agent from modifying critical skills without user approval
- #41939: feat(skills): deterministic opt-in protection for personal skills against agent edits
- PR #26560: fix(skills): block agent mutations of immutable skills
- PR #42223: feat(skills): add deterministic opt-in protection for personal skills

These issues and PRs explore mechanisms to prevent agents from autonomously modifying or creating skills without explicit user confirmation, including locked tiers, protected dotfiles, and confirmation gates for skill mutations.

## TL;DR

- 9 member(s): 2 open issue(s), 3 closed issue(s), 2 open PR(s), 0 merged PR(s), 2 PR(s) closed without merging.
- No fix has been merged to main; one or more PRs were attempted (see below).
- **Recommended:** review the prior/competing PR(s) below. A fix was attempted but not merged; your case may extend or revive that work.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `unresolved`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_PARTIAL`): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.
- Members outside that structural core may belong to a different underlying problem.
- Pairwise link density `0.15`: the share of member pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. `1.00` means every pair is linked.

## Open related issues

- #25083: Feature: Immutable/protected skills - prevent agent from modifying critical skills without user approval
- #41939: feat(skills): deterministic opt-in protection for personal skills against agent edits

## Closed / duplicate issues

- #17583: Skills: user-locked vs self-improving tiers + user-feedback-driven skill updates
- #21315: \[Feature\]: Add \`skills.evolution_mode\` — confirmation gate for autonomous skill evolution
- #26298: \[Feature\]: skill creation should ask user for confirmation — especially when a同名 skill already exists

## Prior & competing PRs

- **#17609: feat(skills): add user-lock and approval gate for skill mutations**. closed without merge
  - maintainer direction: category `uncategorized`; implication `needs_llm`
- **#26547: fix(skills): gate background review writes behind approval**. closed without merge
  - maintainer direction: category `silent_close`; implication `active`
- **#26560: fix(skills): block agent mutations of immutable skills**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `tests/tools/test_skill_manager_tool.py`, `tools/skill_manager_tool.py`
- **#42223: feat(skills): add deterministic opt-in protection for personal skills**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `hermes_cli/commands.py`, `hermes_cli/skills_hub.py`, `hermes_cli/subcommands/skills.py`, `tests/tools/test_skill_manager_tool.py`, `tools/skill_manager_tool.py`, `tools/skills_tool.py`

## Fix status

- No merged fix on record.
- Subsystem: `skills`