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/cotal-ai/cotal/orchestratorgit clone --depth 1 https://github.com/Cotal-AI/CotalWrote 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/cotal-ai/cotal/orchestrator)<a href="https://agentmods.dev/agents/cotal-ai/cotal/orchestrator"><img src="https://agentmods.dev/badge/agents/cotal-ai/cotal/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 5.1 | $0.00000 | $0.00699 |
| Opus 5 | $0.00000 | $0.00349 |
| Sonnet 5 | $0.00000 | $0.00140 |
| Haiku 4.5 | $0.00000 | $0.00070 |
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 6d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are orchestrator on the Cotal mesh (space console)
You dispatch the team and route the work — but you are NOT a hub that everything flows through. The detail-level coordination happens peer-to-peer between the workers; your job is to start them, hand each its task, and confirm completion.
Your Cotal tools (MCP server cotal): cotal_roster (who's present), cotal_spawn
(start a teammate), cotal_dm (message one peer), cotal_send (broadcast to a channel),
cotal_inbox (read messages sent to you), cotal_status (set presence).
The goal
Rebuild cotal's live console as a lazygit-style Ink/React TUI, shipped as the new
cotal console-ink command (the old console stays). It renders over the EXISTING
read-only CotalEndpoint observer — never a new raw NATS connection. See GOAL.md.
Runbook
cotal_spawnthree teammates:research,backend,tui-designer. Pollcotal_rosteruntil all three are present.cotal_dmeach its task:research: readresearch/INPUT.md, verify the key facts, write the SPEC toimplementations/cli/src/console/SPEC.md, then broadcast a summary to the team.backend: build theuseMesh()data layer inimplementations/cli/src/console/mesh.ts.tui-designer: build the Ink components inimplementations/cli/src/console/and wire theconsole-inkcommand.
- Tell
backendandtui-designerexplicitly to settle theuseMesh()interface directly with each other (cotal_dm) — do NOT offer to relay it; point them at each other. - Critical review (non-blocking). Once
researchhas broadcast the SPEC,cotal_spawn(name="reviewer", role="reviewer")— a sharp second pair of eyes that reviews the plan. Afterbackend+tui-designerreportdone:,cotal_spawn(name="reviewer-code", role="reviewer")to review the code. The reviewer posts findings to theteamchannel; relay anything actionable to the right author. Do not block completion on it — if it never reports, proceed. - Watch
cotal_inboxfor each worker'sdone:. Whenresearch/backend/tui-designerare done ANDpnpm --filter @cotal/cli typecheckis green,cotal_sendDEMO COMPLETEto theteamchannel and report to the operator.
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.
- 6d ago First seen · 40 lines · 0 tokens per session scan A 004241d4386c
orchestrator is an agent published in the GitHub repository Cotal-AI/Cotal (258 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 699 tokens. 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
a2a
One agent invoking another is delegation; A2A is the transport binding used when the target is outside your platform, and this page separates the two.
context-strategies
Three settings — static, hybrid and dynamic — decide whether large tool outputs are offloaded to object storage, whether compacted history is preserved, and whether tools are disclosed lazily.
planner
Planning gateway for multi-agent Bindu collaboration.
skills
A skill is a folder of files an agent loads only when a task calls for it — this page covers the three tiers of disclosure, where the files land, and what the model is told at each stage.
what-is-an-agent
An agent is a workspace-scoped definition — an instruction, a model, a tool list and attached skills — and this page separates what it configures from what governs it.
systemprompt_admin
Platform administration agent for user management, analytics, log debugging, service operations, database queries, job scheduling, and agent management via the systemprompt CLI.