Skip to content

chore(.claude/settings): add explicit zflash + zflash-setup permissions (Aaron-authored)#4999

Merged
AceHack merged 1 commit into
mainfrom
chore/zflash-explicit-permissions-aaron-2026-05-25
May 25, 2026
Merged

chore(.claude/settings): add explicit zflash + zflash-setup permissions (Aaron-authored)#4999
AceHack merged 1 commit into
mainfrom
chore/zflash-explicit-permissions-aaron-2026-05-25

Conversation

@AceHack
Copy link
Copy Markdown
Member

@AceHack AceHack commented May 25, 2026

Summary

Adds two explicit narrow permission patterns to .claude/settings.json:

"Bash(bun full-ai-cluster/tools/zflash.ts *)",
"Bash(bun full-ai-cluster/tools/zflash-setup.ts *)",

Functionally redundant with the existing Bash(bun *) wildcard, but explicit narrow patterns serve as:

  1. Audit-trail documentation in settings.json showing which specific destructive-op scripts are operator-authorized (matches B-0728's destructive-tool authoring contract header convention)
  2. Auto-classifier-friendly — narrow explicit patterns are less likely to trigger conservative-default-deny under stricter classifier modes
  3. Knights-Guild-reviewable authorization perimeter visible at a glance instead of inferred from a wildcard

Aaron-authored

Aaron made the edit himself in a worktree I opened for him (operator-side work per the classifier-bypass-research + human-audit-and-legal-risk-acceptance discipline). Committing on his authorization ("okay we have it").

Composes with

Test plan

  • Diff is exactly 2 lines added (no other changes)
  • Lines syntactically valid JSON (preserved by VS Code save)
  • No code changes; pure settings.json hygiene

🤖 Generated with Claude Code

…ns (aaron-authored)

Two explicit narrow permission patterns matching the convention from
B-0728's destructive-tool authoring contract header:

  'Bash(bun full-ai-cluster/tools/zflash.ts *)'
  'Bash(bun full-ai-cluster/tools/zflash-setup.ts *)'

Functionally covered by the existing broader 'Bash(bun *)' wildcard, but
the explicit narrow patterns serve as:

  1. Audit-trail documentation in settings.json showing which specific
     destructive-op scripts are operator-authorized
  2. Auto-classifier-friendly (narrow explicit patterns are less likely
     to trigger conservative-default-deny than broad wildcards under
     stricter classifier modes)
  3. Knights-Guild-reviewable authorization perimeter visible at a
     glance instead of inferred from the wildcard

Pattern future destructive-tool wrappers (zformat, zwipe, etc.) follow:
each gets its own explicit line.

Aaron-authored edit (he made the edit in a worktree I opened for him);
committing per his 'okay we have it' authorization.

Co-Authored-By: Claude <noreply@anthropic.com>
Copilot AI review requested due to automatic review settings May 25, 2026 21:38
@AceHack AceHack enabled auto-merge (squash) May 25, 2026 21:38
Copy link
Copy Markdown

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR updates the Claude tool permissions allowlist to explicitly authorize two bun-invoked zflash-related scripts, making the intended destructive-tool authorization perimeter more visible and classifier-friendly (even though Bash(bun *) already permits them).

Changes:

  • Add explicit Bash(bun full-ai-cluster/tools/zflash.ts *) allow pattern.
  • Add explicit Bash(bun full-ai-cluster/tools/zflash-setup.ts *) allow pattern.

Comment thread .claude/settings.json
@AceHack
Copy link
Copy Markdown
Member Author

AceHack commented May 25, 2026

Verified Copilot finding: zflash.ts + zflash-setup.ts aren't on this branch — they land in companion PR #4997 (B-0737). PR description names this explicitly as the forward-looking authorization pattern. Resolving no-op.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants