Cairn

Claude Code skill permission prompt docs and fixes

NousResearch/hermes-agent · cluster 113447

Data as of

Nothing open on GitHub. Fix merged in #114777. Check it covers your case.

The short answer

0open issues
0open PRs
5items grouped
Known?
Yes. 5 related items grouped here, 1 issue already closed.
Fix event
A fix was merged to main in PR #114777. Check it covers your case. No release data is tracked.
Tracker
The maintainers' tracker marks this resolved, deciding PR #114781. That is separate from the fix event.
Still open
Nothing open on GitHub.

These items address documentation and behavior around Claude Code's permission prompting defaults, clarifying that bypassing prompts is an explicit opt-in rather than the default, and fixing related shell snippet and platform-targeting issues in skill docs.

Open issues0

No open issues.

Open PRs0

No open pull requests.

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

  • #114777 fix(skills): shell snippets paste cleanly and OS-bound skills stop claiming platforms they cannot run on (#113448, #113449, salvage #113710, #113464)

    merged to main

    files: contributors/emails/[redacted:email], optional-skills/creative/heartmula/SKILL.md, optional-skills/mlops/evaluation/evaluating-llms-harness/SKILL.md, optional-skills/mlops/tensorrt-llm/SKILL.md, skills/productivity/notion/SKILL.md, tests/skills/test_authoring_standards.py, tests/skills/test_skill_platform_gates.py, website/docs/user-guide/skills/bundled/productivity/productivity-notion.md, website/docs/user-guide/skills/optional/creative/creative-heartmula.md, website/docs/user-guide/skills/optional/mlops/mlops-evaluation-evaluating-llms-harness.md, website/docs/user-guide/skills/optional/mlops/mlops-tensorrt-llm.md

  • #114781 docs(skills): coding-agent delegation skill defaults to permission prompts; bypass is an explicit opt-in (#113447, salvage #113464)

    merged to main

    files: skills/autonomous-ai-agents/claude-code/SKILL.md, website/docs/user-guide/skills/bundled/autonomous-ai-agents/autonomous-ai-agents-claude-code.md

2 PRs closed without merging

From the close comments: merged via another change 1 · superseded by another PR 1

  • #113456 docs(claude-code): default to permission prompts · superseded by another PR → c55b5bb, #114781, #113447, #113464
  • #113464 docs(skills): fix three doc-class issues from skill audit · merged via another change → 8fb12bc, #114777, #113448, #113449, #113710, #113464
Closed issues · 1
  • Closed#113447[Bug]: claude-code skill standardizes on `--dangerously-skip-permissions` as the default flow
How this cluster was grouped
  • Link evidence (structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
  • Pairwise link density 0.40: the share of item 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.

Pick up a Lab task

Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.

Open the Lab

At a glance

Merged PRs
#114777, #114781
Closed issues
1
Attempts
2 PRs closed without merging
Fix link checked
18 Sep 2026

For your agent

The same facts, typed.

cluster/113447.json
cluster/113447.md