Hephaestus Build

Hephaestus Build

Procedure

1. Treat this as the public Codex build surface. Do not expose or ask the user

to invoke the older internal support skill names.

1. Read AGENTS.md and .agentlas/mode-map.json when they exist in the

current workspace.

1. Run the public mode classifier by independent ownership boundaries, not by

keywords such as "team":

• package or repair existing material -> 30-agentlas-packager;
• one independently owned context/tools/success standard ->

10-single-agent-builder;

• two or more roles with separate context, permissions, success standards,

handoff, or synthesis needs -> 20-multi-agent-team-builder. If the shape is unclear, ask before generating. The user-facing question must be plain language, for example: "이 일을 한 명의 전문가가 처음부터 끝까지 맡으면 되나요, 아니면 조사/분석/검토처럼 여러 전문가가 나눠 맡고 마지막에 합쳐야 하나요?" Do not expose internal labels such as single-agent, team-builder, ownership boundary, memory/context, synthesis, or produces/consumes.

1. Run the Builder Interview and Research Gate from

docs/builder-interview-research-gate.md before writing substantial package files:

• ask an 8-12 question first batch when the request is vague;
• continue follow-ups until target user, tasks, inputs, outputs, examples,

role count, separated tools or permissions, final merge needs, execution order, memory, failure modes, and evals are clear;

• phrase shape questions in everyday language. Ask who handles which part,

whether each role needs different files/accounts/tools, whether someone must merge the result, and whether work can run at the same time or must pass from one person to the next;

• research official or primary docs, similar agent repositories or

comparables, GitHub examples, academic/professional theory, and tool/plugin docs;

• compare selected and rejected tools/plugins with permission, secret,

fallback, and smoke-test notes;

• synthesize domain-expert behavior from interview answers, comparable

agents/repos, theory, and tool choices;

• write docs/builder-interview.md, docs/research-sources.md,

docs/tool-selection.md, docs/domain-expert-synthesis.md, docs/prompt-performance-contract.md, and .agentlas/capability-eval-plan.json.

1. If missing narrow details still change files, adapters, or public/private

boundaries, ask one to five clarify questions before generating.

1. Pick one:

• 10-single-agent-builder;
• 20-multi-agent-team-builder;
• 30-agentlas-packager.

1. Load matching support skills.
2. Emit or repair Agentlas contracts, including .agentlas activation seed

files and .agentlas/global-commands.json when local continuity is part of the output.

1. Add the generated command to Claude Code, Codex, Gemini CLI, generic

AGENTS.md, and terminal adapters. For teams, expose the orchestrator/HQ command and route workers through HQ unless direct worker commands were requested.

1. Run scripts/verify-team-package.sh for generated

or repaired packages. If it fails, do not report completion; collapse the output to a single-agent package or add the required orchestrator/HQ and team contracts.

1. Verify with scripts/verify-package.sh.

Output

Return status, evidence, output, global_commands, interview_research, and blockers.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: agentlas-ai
• Source: agentlas-ai/Hephaestus
• License: Apache-2.0
• Homepage: https://agentlas.cloud

Install and usage instructions live in the source repository linked above.