// Creates, reviews, and dispatches atomic work packets. Every task with a side effect requires an APPROVED packet before execution. Scope is immutable after approval — expansion requires a new packet.
| name | packet-factory |
| version | 1.0.0 |
| description | Creates, reviews, and dispatches atomic work packets. Every task with a side effect requires an APPROVED packet before execution. Scope is immutable after approval — expansion requires a new packet. |
The packet factory is the gatekeeper between intent and execution. Nothing with a side effect runs without an APPROVED packet.
# Create a new packet (DRAFT status)
skills/packet-factory/new-packet.sh \
--intent "Post daily update to Slack #arc-angels" \
--source "Ludo DM 2026-04-01 09:00" \
--destination "Slack #arc-angels"
# Review a packet (set APPROVED or REJECTED)
skills/packet-factory/review-packet.sh --id 2026-04-01-001
# Dispatch an APPROVED packet (executes and logs output)
skills/packet-factory/dispatch-packet.sh --id 2026-04-01-001
All in-flight packets live in memory/packet-queue.md.
The heartbeat pre-flight check reads this file. DRAFT packets older than 24h are escalated to Ludo.
Once a packet is APPROVED, scope_locked_at is set and the scope field is frozen.
If the task grows (new deliverable discovered, Ludo asks for something extra), the current packet is dispatched as-is and a new packet is created for the expansion. Never mutate an approved packet's intent or output.
This prevents the single most common failure mode: scope creep → context balloon → session death.
Creates and configures agent.yaml files, writes SOUL.md personality definitions, and sets up agent directory structures with skills, tools, and knowledge. Use when the user wants to configure an agent, create agent.yaml, write SOUL.md, set up agent directory structure, or customize agent settings.
Converts agent definitions between frameworks — exports to Claude Code, OpenAI, CrewAI, Lyzr, and GitHub Models formats, and imports from Claude, Cursor, and CrewAI projects. Use when the user wants to convert an agent, migrate to another framework, export to LangChain/AutoGen/CrewAI, or import from existing automation tools.
Guides installation of gitagent and creation of first agent with scaffolding, configuration, and validation. Use when the user is new to gitagent, asks how to get started, wants to install gitagent, set up their first agent, or says 'how do I start?'
Searches the SkillsMP registry, installs skills locally or globally, creates custom skills with SKILL.md frontmatter, and manages the skill lifecycle. Use when the user wants to find skills, add new capabilities, install a skill, browse available skills, create a custom skill, or manage the skills system.
Configures and runs agents with different adapters including Claude, OpenAI, CrewAI, Lyzr, and GitHub Models. Supports local execution, remote git repos, and one-shot prompts. Use when the user wants to run an agent, switch LLM providers, configure adapter settings, or launch agents from git repositories.
Model selection by provider health, not task complexity. Tier 0 (local) handles most tasks. Paid models are break-glass only. Fallbacks activate on 429 or timeout — never on perceived task difficulty.