Agentctl v0.5.0

@lab42/agentctl v0.5.0

What's new since v0.4.0:

Features

• JSON Schemas for .ai/ files — config.yaml, permissions.yaml, and mcp.yaml now have JSON Schemas, so editors (VS Code, JetBrains) get autocomplete, inline validation, and hover docs. Stub files ship with a # yaml-language-server: $schema=... comment as a fallback, and the schemas are pending registration in SchemaStore for zero-config detection. (#37, #53, #54)
• Cross-runtime consistency audit — agentctl audit checks that a command resolves to the same permission decision across every enabled runtime and flags divergences by severity (critical/warning/info). (#47)
• Explain permission decisions — agentctl explain <command> shows how a shell command is evaluated under deny_over_allow, including which pattern matched and why. (#46)
• Pre-commit hook setup — agentctl init --with-hooks auto-detects your hook manager (lefthook, husky, simple-git-hooks, or a raw .git/hooks fallback) and wires up agentctl check so drift is caught before commit. (#52)
• Better error messages — parse and validation failures now cite the file, line, and a contextual snippet with a fix suggestion. (#51)

New commands

• agentctl audit — report cross-runtime permission divergences (exit 1 on critical)
• agentctl explain <command> — show the permission decision and matched pattern for a command
• agentctl init --with-hooks — set up a pre-commit hook running agentctl check

Docs

• init now promotes npx @lab42/agentctl as the primary install path. (#50)
• Added a Code of Conduct.

Upgrading

No breaking changes. Generated output is unchanged from v0.4.x.

pnpm add -D @lab42/agentctl@0.5.0

Agentctl v0.4.0

@lab42/agentctl v0.4.0

What's new since v0.3.0:

Features

• Watch mode — agentctl sync --watch auto-syncs when .ai/ files change (#43)
• Auto .gitignore — agentctl init now adds generated paths to .gitignore automatically (#42)
• Permission presets — agentctl init --preset <readonly|standard|trusted> for quick setup (#41)
• Instruction file management — define runtime-aware instructions in .ai/instructions.md, rendered per-runtime as CLAUDE.md, AGENTS.md, .cursor/rules/, .kiro/steering/ (#40)

New commands

• agentctl sync --watch — live-reload on .ai/ changes
• agentctl init --preset <name> — bootstrap with predefined permission sets
• agentctl init --list-presets — show available presets
• agentctl init --no-gitignore — skip .gitignore update

Internal

• Unified Adapter interface — each adapter is now one self-contained file with render, parse, paths, and owns. Adding a new runtime = implement one interface. Massively simplifies scan.ts and cli.ts. (#28)

Upgrading

No breaking changes. Generated output is identical to v0.3.x.

pnpm add -D @lab42/agentctl@0.4.0

v0.2.5

What's Changed

• Bump actions/checkout from 4 to 7 by @dependabot[bot] in #6
• Bump actions/setup-node from 4 to 7 by @dependabot[bot] in #5
• Bump softprops/action-gh-release from 2 to 3 by @dependabot[bot] in #4
• Bump pnpm/action-setup from 4 to 6 by @dependabot[bot] in #3
• Feat agentctl status one line summary of runtime by @iamarpitpatidar in #11
• feat(scan): add agentctl scan to import existing runtime configs by @iamarpitpatidar in #12
• feat(cursor): add Cursor adapter generating .cursor/rules/ by @iamarpitpatidar in #13

New Contributors

• @iamarpitpatidar made their first contribution in #11

Full Changelog: 0.2.4...v0.2.5

v0.2.4

Full Changelog: v0.2.3...v0.2.4

v0.2.3

Full Changelog: v0.2.3-rc.7...v0.2.3

v.0.2.6

Full Changelog: v0.2.5...v.0.2.6