Skip to content
cccskills
FreePublished on GitHub

init

Initialize the standard Interlateral two-agent CLI mesh from a bootstrap agent by running me.sh, launching Claude Opus 4.7 plus Codex 5.5, proving live ACK, and waiting for "Reporting for Duty!". The bootstrap agent is not part of the mesh.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md3.8 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Init

Purpose

Use this skill when a fresh bootstrap agent is asked to initialize the normal Interlateral CLI mesh.

This skill starts exactly the standard duo:

  • Claude Code in ia-claude
  • Codex in ia-codex

It does not launch Gemini CLI, Antigravity CLI, Antigravity Desktop, desktop inbox peers, or extra workers. Those peers are opt-in only when Principal Human explicitly selects them outside the standard init flow.

The agent running this skill is the bootstrap operator. It is not a mesh peer and should not claim a mesh identity.

Boundaries

Do not use this skill for:

  • desktop peers
  • quartet teams
  • extra workers
  • Gemini or Antigravity peers
  • sprint role assignment
  • long-running collaboration patterns

For desktop peers, use desktop-mesh-peer. For transport details, live comms mechanics, ACK proof, direct-send rules, and troubleshooting, use mesh-comms-core. For quartet work, use ready-rock-quartet.

init is the normal CLI bootstrap entrypoint. It also orients operators to the rest of the live-comms skill map: desktop-mesh-peer for Claude Desktop or Codex Desktop, and mesh-comms-core for the shared tmux/direct-injection substrate.

Defaults

me.sh owns the launch mechanics and prints the exact commands before starting the sessions.

Defaults:

  • Claude model: claude-opus-4-7
  • Codex model: gpt-5.5
  • Ready phrase: Reporting for Duty!
  • tmux socket: /tmp/interlateral-agents-tmux.sock

Model and argument defaults are configurable with environment variables:

CLAUDE_MODEL=claude-opus-4-7 CODEX_MODEL=gpt-5.5 ./me.sh
CLAUDE_ARGS="..." CODEX_ARGS="..." ./me.sh

Procedure

  1. Change to the agents repo:
cd path/to/interlateral_agents
  1. Run the standard initializer:
./me.sh

Use ./me.sh --force only when the human explicitly accepts replacing attached ia-claude or ia-codex windows.

  1. Read the preflight output before the sessions launch.

Confirm it prints:

  • detected CLI versions
  • actual Claude launch command
  • actual Codex launch command
  • the configured ready phrase
  1. Wait for both sessions to report:
Reporting for Duty!
  1. Verify the ACK path if either side looks uncertain:
tmux -S /tmp/interlateral-agents-tmux.sock list-sessions
tail -40 interlateral_dna/comms.md

The comms log should contain a stamped Claude ACK to Codex and a stamped Codex ACK to Claude.

Failure Handling

If startup fails:

  1. Inspect the printed launch command and the relevant pane output.
  2. Check interlateral_dna/claude_telemetry.log and interlateral_dna/codex_telemetry.log.
  3. If the run produced half-started sessions, shut down only the launcher-owned duo:
source scripts/tmux-config.sh
run_tmux kill-session -t "$CC_SESSION" 2>/dev/null || true
run_tmux kill-session -t "$CODEX_SESSION" 2>/dev/null || true

Do not use scripts/shutdown.sh for this scoped cleanup. That script intentionally tears down every session on the shared socket.

  1. Retry once with corrected model or argument environment variables.

Do not improvise new mesh topology inside this skill. Escalate if the standard duo cannot boot cleanly after one controlled retry.

Report Format

When complete, report:

INIT_STATUS: READY
BOOTSTRAP_AGENT_IN_MESH: no
SOCKET: /tmp/interlateral-agents-tmux.sock
CLAUDE_SESSION: ia-claude
CODEX_SESSION: ia-codex
READY_PHRASE: Reporting for Duty!
ACK_STATUS: direct plus ledger confirmed

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Method for adding agent comments and work to a shared file without overlapping other agents. Creates isolated workspaces per agent with UTC timestamps. Use when told to add comments, reviews, or work to any file.

The English summary is being prepared. Showing the original description.

dazzaji/interlateral_agents11Updated Sep 28, 2026

Check any artifact against an explicit specification and report adherence using the add-comments workspace format. Use when validating plans, scripts, docs, or code changes against a source-of-truth spec.

The English summary is being prepared. Showing the original description.

dazzaji/interlateral_agents11Updated Sep 28, 2026

Join the Antigravity CLI (agy, Gemini 3.5 Flash) to the Interlateral mesh as a native CLI peer with its own tmux session, identity stamping, and the agy.js send helper. Use this instead of the Antigravity desktop-app CDP path.

The English summary is being prepared. Showing the original description.

dazzaji/interlateral_agents11Updated Sep 28, 2026

Agents work in parallel on the same task; judges evaluate and select the winner.

The English summary is being prepared. Showing the original description.

dazzaji/interlateral_agents11Updated Sep 28, 2026

Boot the explicitly selected CLI(s) as the human's concierge: a project-aware side channel that sits ABOVE the running agent system in a shared writable terminal. It answers status questions and handles the human's ad hoc tasking while the working agents collaborate on the mesh — it is not a worker, manager, or gatekeeper, and team progress never waits for it.

The English summary is being prepared. Showing the original description.

dazzaji/interlateral_agents11Updated Sep 28, 2026

Multiple agents draft a structured document through federated co-authorship and formal voting.

The English summary is being prepared. Showing the original description.

dazzaji/interlateral_agents11Updated Sep 28, 2026

See all skills by dazzaji

Report a problem with this skill