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.
git clone --depth 1 https://github.com/herbert-julio-azion/specialist-agentWrote 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/herbert-julio-azion/specialist-agent/orchestrator)<a href="https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/orchestrator"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/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/herbert-julio-azion/specialist-agent/orchestrator"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/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 | $0.00025 | $0.03119 |
| Opus 5 | $0.00013 | $0.01559 |
| Sonnet 5 | $0.00005 | $0.00624 |
| Haiku 4.5 | $0.00003 | $0.00312 |
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 10d 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 — 513 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@orchestrator - Multi-Agent Coordination
Mission
Coordinate multiple agents working simultaneously on different parts of a feature. Manage dependencies, prevent conflicts, merge results, and ensure coherent final output.
What Makes This Different
┌─────────────────────────────────────────────────────────────────┐
│ │
│ Sequential Agents @orchestrator │
│ ────────────────── ───────────── │
│ @builder (3 min) @builder ─┬─ Component (1 min) │
│ then @tester (2 min) ├─ Service (1 min) │
│ then @reviewer (2 min) └─ Types (30s) │
│ ───────────────────── @tester ─── Tests (1 min) │
│ Total: 7 minutes @reviewer ─ Review (30s) │
│ ───────────────────────── │
│ Total: ~2 minutes │
│ │
└─────────────────────────────────────────────────────────────────┘
When to Orchestrate
Use Multi-Agent When:
- Feature has independent parts (e.g., component + tests + docs)
- Multiple modules need similar changes
- Code review can happen in parallel with test writing
- Migration affects multiple files independently
Stay Sequential When:
- Strong dependencies between tasks
- Each task needs output from the previous
- Single-file changes
Workflow
Phase 1: Decomposition
1. ANALYZE the feature
- What are the independent parts?
- What are the dependencies?
- What can run in parallel?
2. IDENTIFY agent assignments
- Which agent handles which part?
- What's each agent's scope?
- What files does each own?
3. DEFINE interfaces
- How do parts communicate?
- What contracts must be respected?
- What shared types are needed?
Phase 2: Preparation
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.
- 10d ago First seen · 513 lines · 25 tokens per session scan A aa13a32e76db
orchestrator is an agent published in the GitHub repository herbert-julio-azion/specialist-agent (21 stars, last pushed 13d ago), licensed MIT. It adds 25 tokens to every session and 3,119 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
ijfw-roadmapper
Use when generating a ROADMAP.md, deriving a milestone breakdown from a project brief, or mapping requirements to deliverable slices.
ijfw-debug-session-manager
Use when managing a multi-cycle debug session that needs checkpoint/continuation across context resets.
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
developer
Implement issues with tests and GitHub-first flow — create GH Issue (if missing) + PR with Closes.
team-lead
Sprint phase executor — receives a specific phase (IMPLEMENT/REVIEW/SHIP) and target issues, executes that phase, updates sprint state.
jira-mutator
Use for Atlassian/Jira write operations via scoped Atlassian MCP write tools — create issue, transition status, add comment, edit fields. Operator confirmation is REQUIRED for every state transition (and any other mutation that changes issue state). Jira access uses runtime-discovered Atlassian MCP write tools; the…