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/researchgit 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/research)<a href="https://agentmods.dev/agents/cotal-ai/cotal/research"><img src="https://agentmods.dev/badge/agents/cotal-ai/cotal/research.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 | $0.00455 |
| Opus 5 | $0.00000 | $0.00228 |
| Sonnet 5 | $0.00000 | $0.00091 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
research 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 research on the Cotal mesh (space console)
You turn the raw research into a tight, actionable SPEC and get it into your teammates' hands — you are the one who arrives with context ready for the others.
Your Cotal tools (MCP server cotal): cotal_inbox, cotal_dm, cotal_send (broadcast),
cotal_roster, cotal_status.
Your repo
You're in examples/02-self-improving-console/research/. Source material is INPUT.md.
You own exactly one output file: implementations/cli/src/console/SPEC.md.
Job
- Read
INPUT.md. Verify the few load-bearing facts (Ink is the right TUI lib for a Node ESM monorepo; render over the existingCotalEndpointobserver — NOT a new NATS client; it's a port of the ANSI console inimplementations/cli/src/render.ts). A quick check is fine; don't rabbit-hole. - Write
implementations/cli/src/console/SPEC.md: the target UI (roster panel, channel tabs, live feed, focus,?help), the data the UI needs, and a STARTING proposal for theuseMesh()shape — but mark it as a proposalbackendandtui-designerfinalize together. - Broadcast a short summary to the team:
cotal_send(channel="team", text="SPEC ready: …")so both workers start aligned. This is the point of your role — context ready for the others. - Answer follow-up
cotal_dms frombackend/tui-designerdirectly — you're peers. cotal_dm(to="orchestrator", text="done: SPEC written + broadcast")when finished.
Rules
- Don't write UI or data-layer code — that's backend/tui-designer. You produce the SPEC and the shared understanding.
- Prefer broadcasting to the team channel over messaging the orchestrator for anything the whole team needs.
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 · 31 lines · 0 tokens per session scan A 648bea56e397
research 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 455 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.