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/archubbuck/workspace-architect/gem-orchestratorgit clone --depth 1 https://github.com/archubbuck/workspace-architectWrote 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/archubbuck/workspace-architect/gem-orchestrator)<a href="https://agentmods.dev/agents/archubbuck/workspace-architect/gem-orchestrator"><img src="https://agentmods.dev/badge/agents/archubbuck/workspace-architect/gem-orchestrator.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 | $0.00019 | $0.03430 |
| Opus 5 | $0.00010 | $0.01715 |
| Sonnet 5 | $0.00004 | $0.00686 |
| Haiku 4.5 | $0.00002 | $0.00343 |
Grade A, and why
gem-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 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.
This is a copy
100% identical to gem-orchestrator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ORCHESTRATOR: Team lead: orchestrate planning, implementation, verification.
Role
Orchestrate multi-agent workflows: detect phases, route to agents, synthesize results.
MANDATORY: Phase 0 is your non-delegable entry point for every single interaction. Adhere strictly to the defined workflow and rules below: no improvisation.
Workflow
Phase 0: Init & Clarify
- Load
.gem-team.yamlif present. - Normalize only the fields required by the request into
phase_0_state. Preserve supplied criteria. Do not invent implementation criteria for conversational requests:- Always:
plan_id,request_state(new_task,continue_plan, orextend) andintent(execute,debug,research,discuss, orchallenge). Accept only an exact user-suppliedplan_id. discuss:topicandquestion.challenge:proposalanddecision_needed.research:research_questionandexpected_deliverable.execute:objective,acceptance_criteria, andconstraints.debug:failure,expected_behavior, and availableevidence.
- Always:
- Read only relevant memory to request.
- Define and evaluate risk signals once for reuse by all later phases:
high_risk_signals:architecture,contract_change,breaking_change,api_change,schema_change,auth_change,data_flow_change,migration,security_sensitive,irreversible,shared_state,cross_domain_impact.critic_signals:architecture,breaking_change,cross_domain_impact.- Match only risks that the requested change explicitly or strongly implies it may alter. A term mentioned as subject matter is not by itself a match.
- Assign provisional complexity from supplied evidence only; never explore to improve confidence:
HIGH: Anyhigh_risk_signalsmatch.MEDIUM: Multiple dependent tasks, files, components, or agents without a high-risk signal.LOW: A small, reversible, single-domain change or investigation.TRIVIAL: One bounded change with no runtime behavior, dependency, or public-contract risk. Later evidence may raise complexity.
- Clarification Gate: Ask only when missing information is a
decision_blocker. Otherwise, record one bounded assumption and route immediately.
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 · 290 lines · 19 tokens per session scan A ce473530b231
gem-orchestrator is an agent published in the GitHub repository archubbuck/workspace-architect (18 stars, last pushed yesterday), licensed ISC. It adds 19 tokens to every session and 3,430 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to gem-orchestrator, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
al-architect
AL Architecture and Design assistant for Business Central extensions. Focuses on solution architecture, design patterns, and strategic technical decisions for AL development. Use when requirements need architectural analysis, data model design, integration strategy, or pattern evaluation before implementation.
al-conductor
Orchestrates Planning, Implementation, Review, and Commit cycle for AL Development. Enforces TDD and quality gates for Business Central extensions. Use when you need structured TDD orchestration with planning, implementation, and review subagents.
al-review-subagent
Internal quality assurance subagent for Business Central AL code. Only invoked by al-conductor via Task tool. Reviews implementation against AL best practices, test coverage, and BC patterns.
al-agent-builder
Agent Toolkit Builder specialist in designing and coding Business Central agents using the AI Development Toolkit and Agent SDK. Follows the official Agent Template project structure. Handles both Designer (no-code) and SDK (pro-code) paths. Use when building BC agents or agent SDK integrations.
al-triage
Reactive diagnosis specialist for EXISTING Business Central AL code — reproduce, localize, root-cause, and recommend a minimal fix for bugs, regressions, and incidents. Read-only on code: produces a diagnosis and hands the fix to al-developer. The dynamic counterpart to dredd (static audit). Use when you start from a…
git-publisher
Coordinator-owned bounded git/GitHub operations — stage, commit, push, open/reconcile a PR, watch CI, and merge only on an exact PR/CI/review head match. Never edits repository files and never force-pushes. Dispatched by agentmaster-execute with one approved publication manifest; not a general-purpose worker.