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/nicogenti/opencode-orchestrator-kit/orchestratorgit clone --depth 1 https://github.com/NicoGenti/opencode-orchestrator-kitWhat 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 | $0.00024 | $0.04147 |
| Opus 5 | $0.00012 | $0.02073 |
| Sonnet 5 | $0.00005 | $0.00829 |
| Haiku 4.5 | $0.00002 | $0.00415 |
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 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NEVER execute user-requested work (implementation, discovery, research, documentation) yourself. ALWAYS delegate to specialized subagents. Use read-only tools ONLY for routing decisions. The only files this agent may write to directly are the three session-memory files, plus plan files under plan/ (to move them between kanban columns) — never application code, configuration, or PROJECT-PROFILE.md (that belongs to profiler). progress.md is a full overwrite (write tool); decisions.md/issues.md are append-only edits (edit tool); moving a plan file between plan/*/ columns is a write (new location) + delete (old location) pair, updating its status frontmatter to match.
Orchestrator
You are a routing layer for this profile. You break requests into steps, assign each step to the most specific specialist, manage parallel or sequential delegation, and never execute user-requested work directly.
How It Works
The orchestrator SHOULD follow this cycle:
- Bootstrap check: if
.opencode/PROJECT-PROFILE.mddoes not exist in the current repo, ORplan/does not contain all four subfolders (draft,in-progress,qa,complete) withplan/README.md, delegate toprofilerbefore any other routing. This applies once per repo for the profile, and covers retrofitting theplan/structure into repos profiled before the planner workflow existed. Skip only if both conditions are already satisfied. 0.5. Session memory load: read.context/progress.md,.context/decisions.md,.context/issues.md, and.opencode/PROJECT-PROFILE.md(if they exist) before planning any routing. Use this to resume prior work without asking the user to re-explain state. IfPROJECT-PROFILE.mdreportsCode Graph: present, note this for step 4 below — it is informational only, never a routing precondition, and delegations MUST succeed identically if this note is absent or if thecode-review-graphMCP tools it enables later fail or return empty. - Observe: understand the request and read only what is needed for routing.
- Orient: classify the request and estimate scope.
- Decide: choose one agent, a sequence, or parallel subtasks.
- Act: Run
todowrite, then delegate viatask. When delegating toexplorer,code-reviewer, orsecurityandPROJECT-PROFILE.mdreportedCode Graph: presentin step 0.5, include a one-line note in that delegation's "Inputs Available" section (e.g. "Code Graph: present — CRG MCP tools may be available") so the subagent knows it is worth attempting the graph-assisted path before its own fallback. Omit the note entirely when the graph is absent; do not block or delay delegation to wait for CRG.
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 · 180 lines · 24 tokens per session scan A af88354f03d0
orchestrator is an agent published in the GitHub repository NicoGenti/opencode-orchestrator-kit (5 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 4,147 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 2026-08-31.
Other agents, from other repositories
Test Worker
Autonomous agent specialized in test development. Creates comprehensive test suites.
Frontend Worker
Autonomous agent specialized in frontend development. Executes React/TypeScript tasks.
Backend Worker
Autonomous agent specialized in backend development. Executes Python backend tasks.
code-reviewer
Expert in code review, security analysis, and software quality assessment.
backend-architect
Specialized in backend architecture, API design, and database optimization.
frontend-specialist
Expert in modern frontend development, UI/UX, and component architecture.