moberghr
01Plugin Claude Code
Marketplace for Moberg d.o.o. serious engineering Claude plugins.
6 7d ago A
tokens not measured
original MIT
mtk
02Plugin Claude Code
MTK (Moberg Toolkit) — AI-assisted development toolkit with pluggable tech stacks (.NET, Python, TypeScript). Language-agnostic workflow skills, review agents, and compliance-first workflows.
6 7d ago B
tokens not measured
original MIT
Agent Claude Code
Focused reviewer for slice boundaries, dependency direction, and architectural fit of code changes.
6 7d ago A 20 tokens
original MIT
Agent Claude Code
Strict code reviewer for serious software. Reviews against CLAUDE.md, coding-guidelines.md, architecture-principles.md, and existing codebase patterns. Adversarial persona — finds problems, doesn't approve easily.
6 7d ago A 48 tokens
original MIT
Agent Claude Code
Read-only review lane that mines organizational memory — git history of the touched paths, linked GitHub issues and PR-thread discussions, and prior lessons — for context the implementation may have missed (prior reverts, related open issues, decisions recorded in threads, applicable lessons).
6 7d ago A 57 tokens
original MIT
Agent Claude Code
Fresh, anti-anchored review of a saved plan against the current codebase — does not load lessons, prior reviewer output, or planner rationale.
6 7d ago A 35 tokens
original MIT
Agent Claude Code
Adversarial reviewer that hunts silent failures — empty catches, fallbacks that mask errors, swallowed promise rejections, unjustified linter silences, defaults that hide absence. Read-only.
6 7d ago A 44 tokens
original MIT
Agent Claude Code
Focused reviewer for test coverage, assertion quality, and verification gaps.
6 7d ago A 17 tokens
original MIT
PreToolUse
09Hook Claude Code
Runs before the agent uses a tool for Bash, Edit, Write, Read, Grep, Glob, Bash, Edit and Write tool calls, executing security-gate.sh, interactive-guard.sh, scope-guard.sh, read-guard.sh and rule-trigger.sh (5 commands). From moberghr/mtk-agent-toolkit.
6 7d ago A
tokens not measured
original MIT
PostToolUse
10Hook Claude Code
Runs after a tool call finishes for Read, Edit, Write, Bash, Grep, Glob, Edit, Write and Bash tool calls, executing context-budget.sh, spec-approval-trigger.sh and compress-monitor.sh (3 commands). From moberghr/mtk-agent-toolkit.
6 7d ago A
tokens not measured
copy · 52% MIT
PreCompact
11Hook Claude Code
Runs before the context is compacted, executing pre-compact-snapshot.sh. From moberghr/mtk-agent-toolkit.
6 7d ago A
tokens not measured
copy · 88% MIT
SessionStart
12Hook Claude Code
Runs when a session starts on compact, executing post-compact.sh and rule-trigger.sh with --rearm (2 commands). From moberghr/mtk-agent-toolkit.
6 7d ago A
tokens not measured
original MIT
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing userprompt-dispatch.sh. From moberghr/mtk-agent-toolkit.
6 7d ago A
tokens not measured
original MIT
Stop
14Hook Claude Code
Runs when the agent finishes a response, executing capture-learnings.sh, session-analytics.sh and workflow-continuation.sh (4 commands). From moberghr/mtk-agent-toolkit.
6 7d ago A
tokens not measured
original MIT
Settings file Claude Code
Agent settings declaring 7 hook events (PreToolUse, PostToolUse, PreCompact, SessionStart).
6 7d ago C
tokens not measured
original MIT
batch-fix
16Skill Claude CodeCodex
Corrective batch of multiple small independent fixes (apply review findings, several/multiple fixes across >3 files, no new contract or architecture) — broader than fix, lighter than implement.
6 7d ago B 41 tokens
original MIT
Skill Claude CodeCodex
Use before spec writing when the approach is unclear, multiple designs are plausible, or the engineer wants to explore alternatives before committing.
6 7d ago A 29 tokens
original MIT
Skill Claude CodeCodex
Use periodically or when CLAUDE.md feels stale, drifts from the codebase, or commands break — audits CLAUDE.md against a quality rubric and proposes minimal append-only diffs.
6 7d ago A 45 tokens
original MIT
Skill Claude CodeCodex
Use at the end of a session that surfaced context CLAUDE.md was missing — captures discovered commands, gotchas, and patterns as minimal append-only additions, applied only with approval.
6 7d ago A 43 tokens
original MIT
Skill Claude CodeCodex
Use after implementation is verified and before merge, or when reviewing a PR, to check correctness, security, architecture, and test quality against project standards.
6 7d ago A 35 tokens
original MIT
Skill Claude CodeCodex
Use after a feature or fix is verified and passing to reduce complexity, remove dead code, and improve clarity without changing behavior.
6 7d ago A 30 tokens
original MIT
Skill Claude CodeCodex
Use when starting a session, switching between planning/implementation/review phases, entering unfamiliar code, or when output drifts from project norms.
6 7d ago B 32 tokens
original MIT
Skill Claude CodeCodex
Use when the engineer asks what MTK configuration is active — reports tech stack, references, linter packs, domains, hooks, and rules.
6 7d ago B 32 tokens
original MIT
Skill Claude CodeCodex
Use when the engineer corrects your approach, says "no", "not like that", "stop", or redirects your work — capture the correction as a reusable lesson.
6 7d ago B 39 tokens
original MIT