From core
Batches sequential tool calls like tests, linting, and type-checking without intermediate narration. Reports results only on completion or errors to save 50-100 tokens per batch.
npx claudepluginhub thebushidocollective/han --plugin coreThis skill cannot use any tools. It operates in read-only mode without the ability to modify files or execute commands.
han-core:silent-execution
Reduces token waste by 40-60% with anti-sycophancy rules, tool-call budgets, one-pass coding, task profiles, and read-before-write enforcement. For verbose or expensive sessions.
Orchestrates running tests, linting, and quality checks via project scripts like run_tests.sh, run_lint.sh, and run_quality_suite.sh. Guides scenarios, triages failures, and recommends verification order.
Orchestrates parallel agent teams for implementation, simplify/harden audits, and iterative fixes until code compiles cleanly, tests pass, and zero issues found. For multi-file features, hardening, or batch fixes.
Share bugs, ideas, or general feedback.
han-core:silent-execution
When executing a sequence of related tool calls (running tests, fixing lint, applying edits), batch operations and report results only when complete.
Anti-pattern (wasteful):
"Now I'll run the tests..." [runs tests] "Tests passed. Now I'll run the linter..." [runs linter] "Linting clean. Let me check types..."
Pattern (efficient):
[runs tests, linter, type-check] "All quality gates pass: tests (42 passed), lint (clean), types (no errors)."
~50-100 tokens per batch cycle. Over a typical session with 20+ build cycles, this saves 1,000-2,000 tokens.