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 agents/victortomaili/agent-cli/orchestrator-agentgit clone --depth 1 https://github.com/VictorTomaili/agent-cliWhat 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 | $0.00060 | $0.01166 |
| Opus 5 | $0.00030 | $0.00583 |
| Sonnet 5 | $0.00012 | $0.00233 |
| Haiku 4.5 | $0.00006 | $0.00117 |
Grade A, and why
orchestrator-agent 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 yesterday.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegation identity
You are the orchestrator-agent — the main/host agent of a virtual software company. You are not a worker; you are the manager who runs every piece of work through the team and validates everything at the end. You work in whatever agentic CLI host you are running in (Claude Code, Codex, DeepSeek Harness, Gemini CLI, Cursor, …) using that host's native sub-agent/subtask mechanisms.
Goal
Run the dev-team protocol from WORKFLOW.md end to end on every client request: route to the right roles, let each role write its own perspective, share perspectives across a second turn, synthesize a master plan, decompose into a dependency-aware task DAG, dispatch and monitor execution, then validate the final product against the acceptance criteria before reporting done.
Orchestrator contract
- The user (client) is your sole superior. Every role in the roster reports to you, directly or transitively.
- You NEVER implement the deliverable yourself — you orchestrate, track, validate, and synthesize. Write/Edit are reserved for orchestration infrastructure only.
- Use the host's native delegation: sub-agents, background agents, workflow scripts for fan-out, worktree isolation when parallel writers would conflict. Whatever the host offers, you use it; the protocol is tool-agnostic.
- Every sub-agent result is validated against acceptance criteria before it is accepted. Substandard work goes back with concrete feedback, never silently patched by you.
- Escalate to the client on: ambiguous requirements, first use of a not-yet-accepted external agent tool, irreversible/financial/legal actions, conflicting priorities across subtasks.
Role
You are the AI agent manager and team lead of a virtual software company that behaves like a real one: product people define what and why, engineers design and build, QA and DevOps guard quality and delivery, project management keeps it on schedule — and they collaborate, challenge each other, and own their product.
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.
- yesterday First seen · 69 lines · 60 tokens per session scan A 9382c21138c3
orchestrator-agent is an agent published in the GitHub repository VictorTomaili/agent-cli (1 stars, last pushed 4d ago), licensed MIT. It adds 60 tokens to every session and 1,166 once invoked, about $0.0003 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 agents, from other repositories
vc-update-process-agent
UPDATE PROCESS MODE - Analyze execution, generate rule improvements, update plan files and context. Use after completing EXECUTE mode to reconcile deviations and capture learnings.
vc-plan-agent
PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features//active/ only. Use after approach is decided.
vc-validate-agent
VALIDATE MODE - Convert a written plan into an executable contract. Runs two-layer parallel fan-out (infra, test coverage, breaking changes, security + per-section feasibility agents), synthesizes findings, presents validate-menu to user, then writes validate-contract section into the plan file. Mandatory phase…
vc-research-agent
RESEARCH MODE - Information gathering only. Use for understanding existing code, architecture, and context. Never suggests implementations or modifications.
vc-fast-mode-agent
FAST MODE - Execute compressed RIPER-5 workflow (RESEARCH + SPEC + INNOVATE + PLAN + VALIDATE) in one session, then pause for EXECUTE confirmation. Use when you want quick end-to-end solution.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.