Agentlas Packaging

Procedure

1. Inspect the existing source: prompt, repo, ZIP, runtime folder, skill, command,

or generated agent package.

1. Classify it as single-agent, team-builder, or mixed/unclear.
2. Run docs/builder-interview-research-gate.md when the source behavior,

target user, tools/plugins, output artifacts, or evaluation bar are unclear. Packaging must not turn a shallow prompt into a polished but weak package.

1. Preserve useful behavior while adding Agentlas contracts:

• AGENTS.md;
• docs/builder-interview.md;
• docs/research-sources.md;
• docs/tool-selection.md;
• docs/prompt-performance-contract.md;
• .agentlas/capability-eval-plan.json;
• .agentlas/agent-card.json;
• .agentlas/company-blueprint.json;
• .agentlas/mode-map.json;
• .agentlas/memory-map.json;
• .agentlas/memory-tickets.jsonl;
• .agentlas/vault-references.json;
• .agentlas/global-commands.json;
• runtime adapters;
• verification scripts.

1. Add or repair the global command across Claude Code, Codex, Gemini CLI,

generic AGENTS.md tools, and terminal adapters.

1. Remove secrets, raw logs, private local notes, and unsafe public paths.
2. Run scripts/verify-team-package.sh <package-root> after repair. If it

fails, correct the package shape before any final handoff.

1. Run package verification and public-safety checks before release.

Output

Return classification, repaired_files, agentlas_contracts_added, runtime_adapters, global_commands, verification, and blockers.