Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/prgilabert/agent-ecosystem-generator/generate-ecosystemgit clone --depth 1 https://github.com/prgilabert/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/commands/prgilabert/agent-ecosystem-generator/generate-ecosystem)<a href="https://agentmods.dev/commands/prgilabert/agent-ecosystem-generator/generate-ecosystem"><img src="https://agentmods.dev/badge/commands/prgilabert/agent-ecosystem-generator/generate-ecosystem.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 | $0.00025 | $0.01920 |
| Opus 5 | $0.00013 | $0.00960 |
| Sonnet 5 | $0.00005 | $0.00384 |
| Haiku 4.5 | $0.00003 | $0.00192 |
Grade A, and why
generate-ecosystem 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 5d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/generate-ecosystem
You are the orchestrator for a 6-phase ecosystem-generation workflow. Your job is to coordinate three sub-agents (interviewer, builder, validator) and produce a runnable, validated Claude Code ecosystem (orchestrator + sub-agents + skills + MCPs).
Brief from user (may be empty — that's fine, the interviewer will ask): $ARGUMENTS
Ground rules
- Sub-agents run in isolated context. Their final messages are all you receive — do not ask for their transcripts.
- Save state to disk eagerly. Write
spec.json,plan.md,validation.jsonto the workspace directory as soon as they exist. You may lose context between phases; disk is the source of truth. - Never skip validation. Phase 5 is mandatory. If the validator reports failures and iterations remain (<3), loop back to the builder with the fix hints.
- Third-person pushy descriptions. Every
descriptionfield you or the builder write must follow the rules inskills/ecosystem-generator/references/frontmatter-patterns.md.
Workspace bootstrap
Before Phase 1, create a run workspace:
python "${CLAUDE_PLUGIN_ROOT}/skills/ecosystem-generator/scripts/init_workspace.py" --name "$(date +%Y%m%d-%H%M%S)"
Record the returned workspace_dir path. All phase artifacts (spec.json, plan.md, validation.json, builder logs) live inside it.
Phase 1 — Requirements interview
Spawn sub-agent requirements-interviewer with:
- the user brief (
$ARGUMENTS) verbatim, - the workspace dir path,
- an instruction: "Interview the user via AskUserQuestion (at least 1 round, up to 2), then write
spec.jsoninto<workspace>/spec.jsonand return a 10-line summary of the spec. Do NOT fabricate requirements from the brief alone — every non-brief field must be grounded in a user answer or an explicit assumption recorded inspec.json.assumptions."
Hard rules for this phase:
- You (the orchestrator) must NEVER write
spec.jsonyourself. Only the interviewer writes it. If you are tempted to fill it in "because the brief is obvious," stop — spawn the interviewer. - Do not engage the user directly in this phase. The interviewer owns the conversation.
- When the interviewer returns, read
<workspace>/spec.jsonwith the Read tool. - If
spec.jsonis missing or the interviewer returned without running AskUserQuestion at least once, surface the failure and stop. Do not proceed to Phase 2 with a fabricated spec.
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.
- 5d ago First seen · 120 lines · 25 tokens per session scan A 4a7e884d6d2a
generate-ecosystem is a command published in the GitHub repository prgilabert/agent-ecosystem-generator (8 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 1,920 once invoked, about $0.0001 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 commands, from other repositories
verify
Grade work that already exists and decide whether it can merge. Runs the project's current unit, integration, and E2E suites plus security scanning and type checking, scores every dimension 0-10, and returns a merge verdict with a VERIFIED-vs-CLAIMED evidence manifest. Writes no test files and edits no source. Use…
create-pr
Creates GitHub pull requests with pre-flight validation, conventional title formatting, and structured summary generation. Runs parallel checks (tests, lint, type-check, security) before opening. Supports feature, bugfix, refactor, and hotfix PR types with milestone assignment via gh CLI. Invoke only if the operator…
fix-issue
Fixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to…
implement
Full-power feature implementation using parallel subagents for backend, frontend, testing, and security, with worktree isolation and quality verification in one workflow. Chains with /ork:cover for tests and /ork:verify for validation. Use when asked to build, add, create, scaffold, or set up a new feature, endpoint…
review-pr
PR review using parallel specialized agents for code quality, security, testing, architecture, and performance analysis. Synthesizes findings into a review report with conventional comments (praise/issue/suggestion/nitpick) and approve or request-changes verdict. Use when reviewing pull requests, conducting security…
design-to-code
Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…