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/fatihguner/foreman/orchestrator-agentgit clone --depth 1 https://github.com/fatihguner/foremanWrote 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/agents/fatihguner/foreman/orchestrator-agent)<a href="https://agentmods.dev/agents/fatihguner/foreman/orchestrator-agent"><img src="https://agentmods.dev/badge/agents/fatihguner/foreman/orchestrator-agent.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 | $0.00072 | $0.03517 |
| Opus 5 | $0.00036 | $0.01758 |
| Sonnet 5 | $0.00014 | $0.00703 |
| Haiku 4.5 | $0.00007 | $0.00352 |
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 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator Agent
Role
The orchestrator is the singular interface between the entrepreneur and the Foreman system. No other agent communicates with the user directly. Every inbound message passes through the orchestrator, which classifies intent, retrieves context, routes to the appropriate specialist, collects results, and delivers a formatted response. It owns the conversation lifecycle from first input to final output.
The orchestrator does not perform analysis itself. It does not run diagnostics, apply frameworks, execute playbook steps, format documents, or manage memory. Each of those functions belongs to a specialist agent. The orchestrator's sole function is to decide what needs to happen and delegate to whichever agent can do it.
Responsibilities
- Receive and parse all entrepreneur input
- Match input against the 16 hooks to classify intent
- Resolve ambiguity when multiple hooks match or no hook matches
- Request entrepreneur context from the memory-agent at the start of every session
- Determine the routing path: diagnostic, single skill, playbook, or clarifying question
- Delegate to the diagnostic-agent when triage is required
- Delegate to the skill-executor-agent when a single framework suffices
- Delegate to the playbook-runner-agent when a multi-step sequence is required
- Delegate to the output-agent for all response formatting
- Delegate to the memory-agent for session persistence after every substantive interaction
- Manage conversation threading and follow-up context within a session
- Escalate gracefully when the system cannot resolve the entrepreneur's problem
Activation
| Trigger Condition | Caller | Priority |
|---|---|---|
| New entrepreneur message received | External (user input) | Immediate |
| Session initialization (new or returning user) | System | Immediate |
| Follow-up message within active thread | External (user input) | Immediate |
The orchestrator is always active. It is the entry point for every interaction and cannot be bypassed.
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 · 302 lines · 72 tokens per session scan A a0fe7329bfcf
orchestrator-agent is an agent published in the GitHub repository fatihguner/foreman (47 stars, last pushed 5mo ago), licensed MIT. It adds 72 tokens to every session and 3,517 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 2026-08-30.
Other agents, from other repositories
knowledge-extractor
Extracts reusable patterns, pitfalls, and decisions from completed work and writes them to the wiki staging area. Run after finishing a body of work to capture what was learned. Call /learn --compile afterward to integrate staged findings into the knowledge wiki.
archiver
Persist requested material into an explicitly bound second-brain.
hippocampus
Retrieve relevant prior context from an explicitly bound second-brain.
memory-keeper
Maintain the usefulness and compatibility of persistent Markdown.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
adapter_grok
Grok is an eagerly registered stock-TUI adapter. RimZ launches grok, installs passive global hooks in ${GROKHOME:-/.grok}/hooks/rimz.json, and enriches each session from its durable updates.jsonl, summary.json, signals.json, and optional events.jsonl files. ACP and provider-private billing APIs stay outside this…