pravindurgani

Start Impl — Security skill for Claude Code

Security community

Start an IMPL pane session — read context and execute AUDIT directives.

How to install Start Impl

Installs to ~/.claude/skills/pravindurgani-claude-code-multipane-iterm2-start-impl/SKILL.md

Terminal
mkdir -p ~/.claude/skills/pravindurgani-claude-code-multipane-iterm2-start-impl && curl -fsSL https://raw.githubusercontent.com/pravindurgani/claude-code-multipane-iterm2/HEAD/commands/start-impl.md -o ~/.claude/skills/pravindurgani-claude-code-multipane-iterm2-start-impl/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Start Impl does

description: Start an IMPL pane session — read context and execute AUDIT directives

You are in the IMPL pane. Your role is implementation only. Do not audit your own work.

Pre-flight (MANDATORY — before any other action)

This pane MUST have `HANDOFF_SCOPE` set. If unset, stop and tell the human to run `handoff-use ` first.

: "${HANDOFF_SCOPE:?HANDOFF_SCOPE not set — run 'handoff-use ' in this pane first}"

Then check for the scoped HALT sentinel. A HA

Alternatives in Security

Full documentation available on GitHub

View Source Repository

Related Skills

Start Audit — Security skill for Claude Code

Start Audit

Start an AUDIT pane session — adversarial review + prompt-master directives

Security community
Crewcut Audit — Security skill for Claude Code

Crewcut Audit

Audit the whole session's context budget — what was read, what it cost, what to do about it

Security community
Auditing Agent Config — Security skill for Claude Code

Auditing Agent Config

Audit your Claude setup for drift: redundant skills, dead plugins, bloated CLAUDE.md, session-start pile-up.

Security community
Audit Adapters — Security skill for Claude Code

Audit Adapters

Read the AI Stack Expert agent definition at .claude/agents/ai-stack-expert.md to understand your role, expert

Security community
Postgres — Security skill for Claude Code

Postgres

Execute safe read-only SQL queries against PostgreSQL databases with multi-connection support and defense-in-d

Security community
Context Audit — Security skill for Claude Code

Context Audit

Audit how much input-token bloat the read-guard removes on this repo

Security community

Related Agents

QA Logic — Testing & QA agent for Claude Code

QA Logic

Acceptance tests first, then break-it QA on logic. Use PROACTIVELY at the start of plan/execute — writes one f

Testing & QA community
Self Audit Orchestrator — Security agent for Claude Code

Self Audit Orchestrator

Use this agent at the start of a new 14-day cycle (Day 1), during the cycle to execute the 2-hour sprint, and

Security community
Hatch3r Learnings Loader — Project Management agent for Claude Code

Hatch3r Learnings Loader

Session-start agent that surfaces relevant project learnings, recent decisions, and context from previous sess

Project Management community