hautc-it

hautc-it/cil

Agent

Role: Bounded execution of well-defined implementation tasks.

hautc-it/cil

Agent

Role: Task decomposition and sequenced implementation planning.

hautc-it/cil

Agent

Role: Understand existing code, APIs, and architecture before implementation.

hautc-it/cil

Agent

Role: Validate implementation correctness and catch issues before they ship.

hautc-it/cil

Agent Claude Code

Use for systematic investigation of bugs, test failures, or runtime errors. Reproduces first, then forms 2-3 ranked hypotheses with evidence, investigates code paths and git history, and proposes the minimal fix. Never guesses; never shotgun-debugs. Returns a single report — does not modify code.

hautc-it/cil

Command Claude Code

Detect project type (Node/Python/Rust/Go/mixed) and propose CLAUDE.md + settings.json additions for lint, typecheck, and test commands. Pure inspection — applies nothing without explicit user approval.

hautc-it/cil

Command Claude Code

Generate a conventional commit message for staged changes (feat/fix/refactor/...) and run git commit. Refuses if sensitive files are staged.

hautc-it/cil

Command Claude Code

Structured development cycle — Research → Feasibility → Plan → Implement → Verify with persistent memory and feedback replay.

hautc-it/cil

Command Claude Code

Fast session handover — capture current state and write a resume command for the next session. Use when context is filling up or you need to switch tasks.

hautc-it/cil

Command Claude Code

Persist a single insight, decision, or constraint to long-term memory with auto-classified category and tags.

hautc-it/cil

Command Claude Code

Structured codebase orientation — understand an unfamiliar project before making changes. Maps architecture, conventions, entry points, and gotchas.

hautc-it/cil

Command Claude Code

Project-local release pipeline — bump version, regenerate CHANGELOG from commits since last tag, update README docs for new features (with concrete examples + argument explanations), commit + tag + push, open a PR if on a non-main branch, then hand off a manual npm publish (no token configured yet).

hautc-it/cil

Command Claude Code

Full-text search persistent memory (BM25) and present results grouped by category — decisions, constraints, learnings, tasks.

hautc-it/cil

Command Claude Code

Review the working diff (unstaged + staged) against a correctness, regressions, security, performance, and style checklist.

hautc-it/cil

Command Claude Code

Capture testable acceptance criteria for a feature before implementation. BA hat — ambiguities surfaced, scope bounded, success defined.

hautc-it/cil

Command Claude Code

Generate a test scaffold for a file or function following the testing skill protocol — boundary, happy path, edge cases, error cases. Does not run; produces the file.

hautc-it/cil

Command Claude Code

End-of-session protocol — capture decisions, constraints, learnings, and next-session task; create a session snapshot before context is lost.

hautc-it/cil

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, running cil hook pre-tool-use. From hautc-it/cil.

hautc-it/cil

Hook Claude Code

Runs after a tool call finishes, running cil hook post-tool-use. From hautc-it/cil.

hautc-it/cil

Hook Claude Code

Runs before the context is compacted, running cil hook pre-compact. From hautc-it/cil.

hautc-it/cil

Hook Claude Code

Runs when the agent finishes a response, running cil hook session-stop. From hautc-it/cil.

hautc-it/cil

Hook Claude Code

Runs when you submit a prompt, before the agent sees it, running cil hook user-prompt-submit. From hautc-it/cil.

hautc-it/cil

Settings file Claude Code

Agent settings declaring 5 hook events (PreToolUse, PostToolUse, PreCompact, Stop).

hautc-it/cil

Instructions file

Claude Code instructions for hautc-it/cil, covering response style, output compression, code, security and context engineering — write / select / compress / isolate.