Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add prgilabert/agent-ecosystem-generator/plugin install agent-ecosystem-generatorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/prgilabert/agent-ecosystem-generator/ecosystem-generator)<a href="https://agentmods.dev/skills/prgilabert/agent-ecosystem-generator/ecosystem-generator"><img src="https://agentmods.dev/badge/skills/prgilabert/agent-ecosystem-generator/ecosystem-generator.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00084 | $0.01502 |
| Opus 5 | $0.00042 | $0.00751 |
| Sonnet 5 | $0.00017 | $0.00300 |
| Haiku 4.5 | $0.00008 | $0.00150 |
Grade A, and why
ecosystem-generator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ecosystem Generator
A skill that guides generation of a coordinated orchestrator + N sub-agents + M skills + MCPs ecosystem. Mirrors the /generate-ecosystem slash command so the model auto-triggers when users describe the intent without typing the command.
Purpose
Turn a short brief like "I want a PR review system with three checkers" into a validated ecosystem ready to install (as a plugin) or commit (into .claude/).
When to use
Fire this skill when the user says any of:
- "design a multi-agent system" / "agent team" / "agent orchestrator"
- "scaffold a plugin with N agents" / "bootstrap an orchestrator"
- "create a set of skills that work together"
- "I need a claude code setup that does X and Y and Z"
- "plan a Claude ecosystem for "
Do not fire this skill for single-skill generation — defer to skill-creator instead. If the user explicitly mentions only one agent or only one skill, this is not the right tool.
Workflow
The skill runs the same 6 phases as the orchestrator command. Read commands/generate-ecosystem.md at ${CLAUDE_PLUGIN_ROOT}/commands/generate-ecosystem.md for the canonical flow. The steps:
- Workspace bootstrap —
scripts/init_workspace.pycreates a timestamped workspace dir. - Requirements interview — delegate to the
requirements-interviewersub-agent; read the resultingspec.json. - Architecture — read
references/orchestration-patterns.mdand pick a pattern; enumerate agents/skills/MCPs; writeplan.mdusing the schema inreferences/schemas.md. Checkpoint with the user. - Target pick — ask the user: portable plugin vs. in-project
.claude/. - Build — delegate to
ecosystem-buildersub-agent, which usesscripts/scaffold_plugin.pyorscripts/scaffold_project.py+scripts/scaffold_mcp.py. - Validate — delegate to
ecosystem-validatorsub-agent, which runsscripts/validate_ecosystem.py+scripts/eval_triggers.py. Iterate with the builder up to 3 rounds on failure. - Summary — report paths, file counts by primitive, validation score, install/activation next step.
What ships with it
29 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/mcp-stdio-template/python-fastmcp/pyproject.toml.tpl 291 B
- assets/mcp-stdio-template/python-fastmcp/README.md.tpl 473 B
- assets/mcp-stdio-template/python-fastmcp/server.py.tpl 472 B
- assets/mcp-stdio-template/typescript-sdk/package.json.tpl 479 B
- assets/mcp-stdio-template/typescript-sdk/README.md.tpl 449 B
- assets/mcp-stdio-template/typescript-sdk/src/server.ts.tpl 669 B
- assets/mcp-stdio-template/typescript-sdk/tsconfig.json.tpl 287 B
- assets/plugin-template/.claude-plugin/plugin.json.tpl 198 B
- assets/plugin-template/.mcp.json.tpl 41 B
- assets/plugin-template/agents/agent.md.tpl 293 B
- assets/plugin-template/commands/orchestrator.md.tpl 445 B
- assets/plugin-template/hooks/hooks.json.tpl 30 B
- assets/plugin-template/README.md.tpl 452 B
- assets/plugin-template/skills/SKILL.md.tpl 279 B
- assets/project-config-template/README.md 798 B
- references/frontmatter-patterns.md 3.4 KB
- references/mcp-templates.md 3.9 KB
- references/orchestration-patterns.md 4.1 KB
- references/schemas.md 4.8 KB
- scripts/_post_write_hook.py 2.6 KB runs code
- scripts/eval_triggers.py 7.6 KB runs code
- scripts/init_workspace.py 1.2 KB runs code
- scripts/requirements.txt 12 B
- scripts/scaffold_common.py 8.4 KB runs code
- scripts/scaffold_mcp.py 5.5 KB runs code
- scripts/scaffold_plugin.py 3.3 KB runs code
- scripts/scaffold_project.py 3.5 KB runs code
- scripts/utils.py 5.1 KB runs code
- scripts/validate_ecosystem.py 17 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 99 lines · 84 tokens per session scan A 9dc40838a550
ecosystem-generator is a skill published in the GitHub repository prgilabert/agent-ecosystem-generator (8 stars, last pushed 4mo ago), licensed MIT. It adds 84 tokens to every session and 1,502 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
istio-traffic-management
Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
workflow-orchestration-patterns
Design durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.
ax-agent-rlm
This skill helps an LLM generate correct AxAgent RLM/runtime code using @ax-llm/ax. Use when the user asks about RLM code execution, AxJSRuntime, contextFields, contextPolicy, liveRuntimeState, promptLevel, stage prompt controls, executorModelPolicy, maxRuntimeChars, agent.test(...), llmQuery(...), recursionOptions…
ax-go-flow
Use when writing Go code with github.com/ax-llm/ax/packages/go for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.