{ "applicability": { "image_classes": [ "primus", "agent-latest" ], "roles": [ "operator", "desktop-agent" ], "tool_requirements": [ "python3", "memory-api" ] }, "behavior": { "skill_ref": "payload/SKILL.md" }, "content_hash": "sha256:8a8cc605aacf7ea7142deff35d41dc7ba2aa153d1ac21fd9ac3b1b4d3648bd30", "deployment": { "entrypoint": "Ask your agent to use the agent-scaffold skill, or run: python3 ~/.claude/skills/agent-scaffold/scripts/scaffold.py \"\"", "recipe_ref": "recipe.yaml", "verify_command": "test -f ~/.claude/skills/agent-scaffold/SKILL.md" }, "description": "Installs the agent-scaffold skill: given an agent name and a one-line description, it queries m2-memory (agent.memory.system / memory-api) for relevant context and generates a complete agent workspace \u2014 PRD.md (problem, personas, functional requirements, success metrics), SOUL.md (identity, values, communication style, scope boundaries), and MEMORY.md (seed memories pre-loaded from the search results) \u2014 plus a deploy snippet for OpenClaw or Hermes. Ships two artifacts: SKILL.md and scripts/scaffold.py (a single-file Python script using only the stdlib, talking HTTP to memory-api). Requirement: the buyer machine needs memory-api (m2-memory) network access for full function \u2014 scripts/scaffold.py calls M2_MEMORY_API_URL (default http://172.18.0.20:8000, override via env) at /memory/search. Without reachable memory-api the script still runs and produces PRD.md/SOUL.md, but with an empty 'Relevant Memory Context' section and no MEMORY.md content \u2014 degraded, not blocked. content_hash is computed over payload/ + recipe.yaml only (not solution.json itself, to avoid the self-referential hash problem of hashing a file that contains its own hash): sha256 of `tar --sort=name --mtime='@0' --owner=0 --group=0 --numeric-owner -czf - payload recipe.yaml` run from this bundle's root.", "evidence": [ { "excerpt": "SKILL.md frontmatter: 'Scaffolds OpenClaw/Hermes agent workspaces from m2-memory. Query memory for context, generate PRD.md + SOUL.md for a new agent, and optionally wire into the fleet.'", "machine": "m2", "source": "/home/m2/.claude/skills/agent-scaffold/ (SKILL.md, scripts/scaffold.py) \u2014 the proven skill this bundle packages, present on the m2 host since 2026-04-20 (SKILL.md mtime 2026-04-20T22:48:00+02:00, scripts/scaffold.py mtime 2026-04-28T00:33:10+02:00 \u2014 a later revision of the same script)" }, { "excerpt": "admin-data-bridge/SOUL.md: 'You are the Admin Data Bridge for GMI Clinic... ## Values ## Communication style ## Scope boundaries' \u2014 same section structure generate_soul() in scaffold.py emits", "machine": "m2", "source": "/home/m2/gmi-clinic/agents/{admin-data-bridge,clinical-entity-extraction,drg-los-optimizer}/{PRD.md,SOUL.md} \u2014 three real PRD+SOUL agent-workspace pairs on disk, all created 2026-04-20 22:46:27\u201322:47:19 (mtimes), roughly one minute before this skill's own SKILL.md mtime (22:48:00) \u2014 the exact PRD.md/SOUL.md workspace shape this skill formalizes and automates, produced for the GMI Clinic AI fleet deployment immediately prior to the skill being written" }, { "excerpt": "SKILL.md: 'The goal is reproducibility: if an agent's context is lost (like Nasr's Apr 8 research agents), this skill can reconstruct the workspace from the vector store and hand it to OpenClaw or Hermes to re-execute without starting from scratch.'", "machine": "m2", "source": "/home/m2/gmi-clinic/agents/gesy-research/PRD.md \u2014 a fourth real workspace, mtime 2026-04-20T22:47:48+02:00, whose own text names the exact incident SKILL.md's 'Design principle' section cites as the skill's reason for existing: 'On 2026-04-08, Nasr ran 4 parallel research agents on his machine... The output was intended to be stored in m2-memory, Planka, and Forgejo but the storage step failed (m2 errored). This PRD reconstructs the agent's purpose and gaps so the research can be completed and properly stored.'" }, { "excerpt": "nasr/SOUL.md: 'You are Nasr's digital twin \u2014 his AI counterpart in the Machine.Machine fleet... ## Core Capabilities'", "machine": "m2", "source": "/home/m2/agent-restore-harness/agents/*/SOUL.md \u2014 three further real SOUL.md agent-identity files for actual named fleet agents (machine names withheld from shared catalog per tenant-firewall hygiene), mtimes 2026-04-22T23:41\u20132026-04-23T00:48, confirming the PRD+SOUL workspace pattern stayed in production use after the skill was written, not a one-off" } ], "intent": "Give an operator a reproducible way to stand up (or reconstruct) a new agent's working context \u2014 PRD + identity + seed memory \u2014 from what the fleet's memory system already knows, instead of starting from a blank page.", "license": { "major_version_coverage": true, "terms": "Perpetual use on operator-owned machines for the buyer's own agent-workspace generation; no redistribution of the skill files as a standalone product." }, "name": "Agent Scaffold Generator", "permissions": [ { "action": "write", "target": "~/.claude/skills/agent-scaffold/" }, { "action": "write", "target": "~/agents// (PRD.md, SOUL.md, MEMORY.md \u2014 output of running the skill, not part of the install)" }, { "action": "net", "target": "HTTP POST to the configured M2_MEMORY_API_URL /memory/search endpoint" } ], "price": { "amount": 60, "currency": "m2cr", "model": "fixed" }, "revenue_split": { "platform_pct": 10 }, "runtime": { "surfaces": [ "claude-code-skill" ] }, "schema_version": "m2.solution.v1", "seller": "sdjs-operator", "solution_id": "sol_agent-scaffold", "summary": "Scaffold OpenClaw/Hermes agent workspaces (PRD.md + SOUL.md + MEMORY.md) from m2-memory context.", "tenant_scope": "m2-core", "tools": [ { "kind": "http-api", "name": "memory-api", "required": true }, { "kind": "cli", "name": "python3", "required": true } ] }