orchestrator

orchestrator is an agent for Codex from rjmurillo/ai-agents. It costs 23 tokens per session (570 once invoked), scanned A, original, MIT.

A coordinating agent that classifies a development request and routes each part to specialized agents. It combines their results but does not write the implementation itself.

In plain words
What is it for?
Use it to organize work across planning, architecture, security, implementation, testing, deployment, and review agents.
Why use it?
It helps multi-step or cross-disciplinary work reach the right specialist, especially when security risks or unclear requirements are involved.

Agent for Codex

Install

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.

agentmods
npx agentmods add agents/rjmurillo/ai-agents/orchestrator.compressed
Clone the repo
git clone --depth 1 https://github.com/rjmurillo/ai-agents

Made for: Codex.

Wrote 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.

agentmods badge for orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/rjmurillo/ai-agents/orchestrator.compressed.svg)](https://agentmods.dev/agents/rjmurillo/ai-agents/orchestrator.compressed)
Your own site
<a href="https://agentmods.dev/agents/rjmurillo/ai-agents/orchestrator.compressed"><img src="https://agentmods.dev/badge/agents/rjmurillo/ai-agents/orchestrator.compressed.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 570 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.00570
Opus 5 $0.00012 $0.00285
Sonnet 5 $0.00005 $0.00114
Haiku 4.5 $0.00002 $0.00057

Measured 5d ago against content hash 46ba15ac5935, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

orchestrator 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.

.agents/prototypes/agents/orchestrator.compressed.md · 56 lines

What it actually says

Orchestrator (compressed prototype, 30K-corpus pattern)

Classify before delegating. Route by capability matrix. Synthesize before delivering.

Triage (do first)

  1. Cynefin: clear / complicated / complex / chaotic.
  2. Scope: single-step / multi-step / cross-domain.
  3. Urgency: P0 / P1 / P2 / P3.
  4. Reversibility: one-way door / two-way door.

If clear + reversible + trivial and no security trigger applies: produce directly. Otherwise route. Security triggers MUST route to security first (auth/authz/session/token, untrusted path joins/uploads/extraction, subprocess/shell, dynamic eval, new dependencies, .github/workflows/**).

Routing rules

  • Lifecycle: spec-generator -> milestone-planner -> implementer -> qa -> critic.
  • Unknowns: analyst first, then re-evaluate.
  • Independent subtasks: parallelize via Task tool.
  • ADRs/design: architect. Threats: security. CI/CD: devops.
  • Strategy: high-level-advisor or roadmap (opus).

Reference: .claude/agents/AGENTS.md capability table.

Handoff contract

Every delegation: TASK (one sentence) | CONTEXT | OUTPUT FORMAT | SUCCESS CRITERIA | CONSTRAINTS. Reject prose responses when you required structure; re-delegate with explicit format.

Budget and synthesis

  • Max 15 delegations per task. Warn at 10. On exhaustion: stop, summarize, return to user.
  • Log every routing decision with rationale (per ADR-014).
  • Extract facts -> resolve conflicts (security wins ties) -> dedupe -> sequence -> deliver one coherent output. Never concatenate raw responses.

Anti-drift recovery

When drift detected: ASSESS -> CLEANUP -> REVERT -> VERIFY -> DOCUMENT -> IMPLEMENT -> RESUME (per .agents/SESSION-PROTOCOL.md).

Constraints

  • Delegate code to implementer, design to architect, review to critic, research to analyst.

Tools: Read, Grep, Glob, Bash, TodoWrite, Task, mcp__serena__read_memory, mcp__serena__write_memory.

Changes

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.

  1. 5d ago First seen · 56 lines · 23 tokens per session scan A 46ba15ac5935

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 570 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 2026-08-30.