jnMetaCode/agency-orchestrator is a workflow system that lets people assemble teams of specialized AI roles from a natural-language request and run them against defined tasks and acceptance criteria. It is intended for individuals who want AI collaborators to produce research, content, products or other deliverables through web, desktop, Docker or command-line interfaces. The catalogue add-ons configure the agent roles and workflows used by the orchestrator.
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 skills add jnMetaCode/agency-orchestrator --skill deerflowgit clone --depth 1 https://github.com/jnMetaCode/agency-orchestratorWrote 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/jnmetacode/agency-orchestrator/deerflow)<a href="https://agentmods.dev/skills/jnmetacode/agency-orchestrator/deerflow"><img src="https://agentmods.dev/badge/skills/jnmetacode/agency-orchestrator/deerflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jnmetacode/agency-orchestrator/deerflow"><img src="https://agentmods.dev/badge/skills/jnmetacode/agency-orchestrator/deerflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.00647 |
| Opus 5 | $0.00017 | $0.00324 |
| Sonnet 5 | $0.00007 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
ao-workflow-runner 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 10d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Role Workflow Runner
When the user asks to run a workflow (YAML file) or a multi-role collaboration task, follow these steps:
1. Parse Workflow
Read the specified YAML file. Extract name, inputs, steps, depends_on, conditions, and loops.
2. Collect Inputs
required: trueinputs must be provided by the user- Optional inputs with
defaultuse the default value - Optional inputs without default are set to empty string
3. Build Execution Order
Topological sort by depends_on. Steps without dependencies belong to the same level and can run in parallel.
4. Execute Steps
For each step:
- Read
agency-agents-zh/{role}.md(search order: YAML's agents_dir → ./agency-agents-zh/ → ../agency-agents-zh/ → node_modules/agency-agents-zh/) - Extract all markdown content after the frontmatter (
---) as the role personality - Replace
{{variables}}in the task with context values (from inputs or previous step outputs) - Evaluate conditions: if
conditionis set, evaluate it. Skip the step if the condition is not met. Operators:contains,equals,not_contains,not_equals - Fully embody the role — use that role's expertise, frameworks, and communication style. Output should be substantive.
- Store the step's output text into the context variable (if step has an
outputfield) - Check loops: if
loopis set and exit_condition is not met, jump back toloop.back_tostep (max:loop.max_iterationsrounds)
Label each step: ### Step N/Total: step_id (Role Name)
5. Save Results
Save all outputs to files:
ao-output/{workflow-name}-{date}/
├── steps/
│ ├── 1-{step_id}.md
│ └── ...
├── summary.md # Final step's full output
└── metadata.json # Step states, timing, token counts
6. Suggest Iteration
After completion, always tell the user:
To improve a specific step, ask me to re-run from that step. I'll reuse all upstream outputs. For CLI:
ao run <workflow> --resume last --from <step-id>
What ships with it
1 file 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.
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.
- 10d ago First seen · 56 lines · 34 tokens per session scan A 25ff9a88b380
ao-workflow-runner is a skill published in the GitHub repository jnMetaCode/agency-orchestrator (2,217 stars, last pushed 3d ago), licensed Apache-2.0. It adds 34 tokens to every session and 647 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
ai4j-app-builder
Use this skill when helping users build applications with AI4J in their own Java or Spring Boot projects, including first chat, streaming, tool/function calls, MCP, RAG, memory, Agent runtime, Coding Agent CLI embedding, FlowGram integration, provider configuration, dependency selection, and troubleshooting. It guides…
ask-user-collaboration
Ask the application user concise structured questions when missing information blocks a safe AI4J agent action.
use-v4-flash-worker
Use only for an existing Codex 0.148.x-or-older DeepSeek-backed v4flashworker installation; contains the legacy plaintext-Hook handoff, recovery, and data-boundary contract. On Codex 0.149.0 or later, direct cross-provider work to MixAgents Broker instead.
broker
Delegate bounded work from a Codex controller to configured workers on other model providers without changing the controller's provider. Use when cross-provider delegation, a named Broker route, or a lower-cost/specialized external worker is requested. Do not use for ordinary same-agent work.
email-assistant
A read-only assistant for reviewing incoming Yandex or Gmail messages from a chat.
code-review
A code-review checklist for examining code without rewriting it. It checks correctness, security, readability and performance, then labels findings by seriousness.