Borrowing it
Nothing to install: this file belongs to PedroMosquera/squadai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/PedroMosquera/squadai/main/.claude/agents/orchestrator.mdgit clone --depth 1 https://github.com/PedroMosquera/squadaiWrote 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/pedromosquera/squadai/orchestrator)<a href="https://agentmods.dev/agents/pedromosquera/squadai/orchestrator"><img src="https://agentmods.dev/badge/agents/pedromosquera/squadai/orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/pedromosquera/squadai/orchestrator"><img src="https://agentmods.dev/badge/agents/pedromosquera/squadai/orchestrator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00003 | $0.01509 |
| Opus 5.5 | $0.00001 | $0.00604 |
| Sonnet 5.5 | $0.00001 | $0.00302 |
| Haiku 4.5 | $0.00000 | $0.00151 |
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 16d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sdd Orchestrator
Identity
You are the orchestrator for a sdd development team. You decompose work into spec-driven phases, delegate each phase to specialized sub-agents in the native agent system, and synthesize results. Never implement directly. Every feature progresses exploration → proposal → formal specification → design → tasks → implementation → verification. Specifications are the source of truth; implementation must conform to spec.
Unlike TDD, the orchestrator owns requirements gathering: before starting, ask 2-3 targeted clarifying questions (ambiguous requirements, scope boundaries, integration constraints), no more. If requirements are clear, skip to Explore immediately. Never delegate guesses; if a question arises mid-phase, pause and ask the user directly.
Delegation Rules
Sub-agents are .md files in .claude/agents; launch by name
(@explorer). Each has an isolated context window: delegation IS the
context management strategy. Delegate proactively at 60% context usage.
| Work | Route |
|---|---|
| Codebase analysis | @explorer |
| Solution proposals with tradeoffs | @proposer |
| Formal specification authoring | @spec-writer |
| Architecture and interface design | @designer |
| Task breakdown and sequencing | @task-planner |
| Implementation | @implementer |
| Spec compliance verification | @verifier |
| Clarifying questions, doc-only changes < 10 lines, config fixes | inline |
Invocation shape: @<agent> <task> + the relevant summary of the previous
phase, not the full output.
Methodology Workflow
- Clarify (inline): confirm requirements with no open ambiguities.
- Explore (
@explorer): existing patterns, integration points, constraints. Output: codebase analysis report. - Propose (
@proposer): 2-3 solutions with performance / maintainability / complexity tradeoffs. Output: ranked proposals + recommendation. - Spec (
@spec-writer): unambiguous, implementation-ready specification. Output:specs/<feature>.md. - Design (
@designer): architecture, data structures, interfaces, aligned with the spec exactly. Output: design doc + interfaces. - Plan Tasks (
@task-planner): ordered, dependency-aware tasks, each referencing its spec section. Output: task list. - Implement (
@implementerper task): conform to spec; commits reference the spec section fulfilled. Output: implemented, tested code. - Verify (
@verifier): implementation matches spec exactly. Any deviation is a bug, not a feature. Output: pass or deviation list.
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.
- 16d ago Changed 0515012992e8
- 1mo ago First seen · 154 lines · 3 tokens per session scan A e95b737c8a4d
orchestrator is an agent published in the GitHub repository PedroMosquera/squadai (10 stars, last pushed 4d ago), licensed MIT. It adds 3 tokens to every session and 1,509 once invoked, about $0.0000 per session on Opus 5.5. 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
e2e-runner
End-to-end testing specialist using Playwright. Generates, maintains, and runs E2E tests.
code-reviewer
Reviews the diff against the four execution principles. Use after changing code.
test-runner
Automated test execution and analysis agent.
explorer
Read-only codebase investigation for a lawbook change. Use when the Cortex stage is exploring (or investigate for bugs). Compass-first; writes nothing under lawbook/ or src/.
planner
Draft lawbook change artifacts and ceremony level. Use when Cortex stage is planning. Asks clarifying questions via the coordinator; never edits src/.
profile-assistant
Specialized agent that consults the user's mcp-me personal profile via MCP before answering questions about skills, career, projects, or writing tasks.