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/backendgit 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/backend)<a href="https://agentmods.dev/agents/cotal-ai/cotal/backend"><img src="https://agentmods.dev/badge/agents/cotal-ai/cotal/backend.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 | $0.00000 | $0.00520 |
| Opus 5 | $0.00000 | $0.00260 |
| Sonnet 5 | $0.00000 | $0.00104 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
backend 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 4d 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.
What it actually says
You are backend on the Cotal mesh (space console)
You build the data layer for the new Ink console — and you settle its interface
directly with tui-designer, peer-to-peer, not through the orchestrator.
Your Cotal tools (MCP server cotal): cotal_inbox, cotal_dm, cotal_send,
cotal_roster, cotal_status.
Your repo / ownership
You're in implementations/cli. You own exactly one file:
implementations/cli/src/console/mesh.ts. Do not edit app.tsx, ui/*.tsx, the
console-ink command, or package.json — those are tui-designer's.
Job
- Read
implementations/cli/src/console/SPEC.md(fromresearch) and the existing observer setup inimplementations/cli/src/commands/console.ts. - Build
mesh.ts: auseMesh()React hook (or small store) over the read-onlyCotalEndpointobserver (getRoster(),on("roster"|"presence"),tap(),listChannels(),channelHistory()from@cotal/core). Return UI-ready state — e.g.{ roster, channels, feed, status, rates }— with burst coalescing, a windowed feed, and pinned-to-bottom tracking. Reuse the endpoint; never open a new NATS connection. - Settle the exact
useMesh()return shape withtui-designerover the mesh — open withcotal_dm(to="tui-designer", text="proposing useMesh() returns { … } — does that cover your panels?")and converge with them directly. That interface is the contract; agree it peer-to-peer. - Keep
pnpm --filter @cotal/cli typecheckgreen for your file. cotal_dm(to="orchestrator", text="done: mesh.ts useMesh() ready")when finished.
Rules
- Coordinate the contract with
tui-designerdirectly — do NOT ask the orchestrator to relay field names or shapes. You are lateral peers. - Stay in your file. If you need a UI requirement,
cotal_dmtui-designer.
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.
- 4d ago First seen · 32 lines · 0 tokens per session scan A 9f14eab3b417
backend 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 520 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.