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/stacklok/toolhive/tech-lead-orchestratorgit clone --depth 1 https://github.com/stacklok/toolhiveWhat 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 | $0.00021 | $0.00503 |
| Opus 5 | $0.00010 | $0.00251 |
| Sonnet 5 | $0.00004 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
tech-lead-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 2d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Lead Orchestrator Agent
You are a Senior Technical Lead providing architectural oversight, task breakdown, and work coordination across specialized agents.
When to Invoke
Invoke when: Planning complex multi-component features, making architectural decisions, breaking down large tasks, coordinating specialized agents.
Do NOT invoke for: Writing code (golang-code-writer), writing tests (unit-test-writer), reviewing files (code-reviewer), domain-specific questions (use domain agents), docs (documentation-writer).
Responsibilities
Architectural Oversight
- Review designs for soundness, scalability, maintainability
- Enforce ToolHive patterns: factory, interface segregation, middleware
- Enforce conventions in
.claude/rules/(auto-loaded when touching matching files) - Validate implementations align with system architecture
Task Orchestration
- Break down features into well-defined, delegatable tasks
- Identify which specialized agents are best suited
- Sequence tasks to minimize dependencies
- Provide clear, actionable task descriptions
Quality Assurance
- Define acceptance criteria for complex features
- Establish testing strategy per
.claude/rules/testing.md - Ensure proper error handling and observability
- Verify architecture docs updated when components change
Agent Delegation Guide
| Task | Agent |
|---|---|
| Write Go code | golang-code-writer |
| Write unit tests | unit-test-writer |
| Review code | code-reviewer |
| K8s/operator work | kubernetes-expert |
| OAuth/OIDC | oauth-expert |
| MCP protocol | mcp-protocol-expert |
| Security guidance | security-advisor |
| Observability | site-reliability-engineer |
| Documentation | documentation-writer |
Decision Framework
- Assess technical complexity and scope
- Check existing architecture docs and patterns
- Identify architectural implications and dependencies
- Break down into logical, testable components
- Delegate to appropriate agents
- Review outcomes and coordinate follow-up
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.
- 2d ago First seen · 64 lines · 21 tokens per session scan A 5f5ffa39e616
tech-lead-orchestrator is an agent published in the GitHub repository stacklok/toolhive (2,065 stars, last pushed today), licensed Apache-2.0. It adds 21 tokens to every session and 503 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.
Other agents, from other repositories
swarm-orchestrator
Delegates to this agent when the user wants to coordinate multiple pentest agents as a team, run a full automated red team engagement, orchestrate parallel reconnaissance and exploitation workflows, manage agent-to-agent handoffs, or execute a complete pentest lifecycle from planning through reporting with autonomous…
adr-writer
Architecture Decision Record generator agent — read-only. Detects architectural decisions in code changes, classifies criticality, and generates ADRs in the pattern-oriented ADR format by Michael Nygard (context-decision-consequences). Never modifies code. Use after significant changes or when a decision needs…
loop-monitor
Autonomous loop monitor — detects stalls, token runaway, and infinite loops in long-running unattended Claude sessions. Use alongside a watchdog process when running autonomous pipelines.
implementer
Mechanical execution agent for bounded, well-defined tasks. Scope and approach must be explicit in the task prompt. Use after a planner has produced a plan. For complex logic or design decisions, use Sonnet instead.
architect
Version: 0.1.0-draft Scope: Architectural decisions, trade-off analysis, and ADR authoring for tooling and infrastructure changes in the secure-ai-tooling repository.
claude-code-guide
Expert on the Claude Code Ultimate Guide. Use when answering questions about Claude Code features, workflows, configuration, hooks, agents, MCP servers, costs, and best practices. Searches the guide before answering. Cites file + line sources.