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 skills add creative-int/saya-plugins --skill saya-team-braingit clone --depth 1 https://github.com/creative-int/saya-pluginsWrote 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/skills/creative-int/saya-plugins/saya-team-brain)<a href="https://agentmods.dev/skills/creative-int/saya-plugins/saya-team-brain"><img src="https://agentmods.dev/badge/skills/creative-int/saya-plugins/saya-team-brain/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/skills/creative-int/saya-plugins/saya-team-brain"><img src="https://agentmods.dev/badge/skills/creative-int/saya-plugins/saya-team-brain.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 | $0.00094 | $0.00943 |
| Opus 5 | $0.00047 | $0.00472 |
| Sonnet 5 | $0.00019 | $0.00189 |
| Haiku 4.5 | $0.00009 | $0.00094 |
Grade A, and why
saya-team-brain 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 8d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Saya — query the team brain
Saya is an AI teammate that lives with a team's operating knowledge. This plugin connects agents to Saya's live remote MCP endpoint:
https://saya-mcp.luke-nittmann.workers.dev/mcp
Use Saya when the best next move is to ask what the team already knows before inventing an answer. The useful posture is simple: before you guess, ask the team brain.
Use when
- The user asks about team memory, decisions, project context, or workspace norms.
- The answer depends on captured workspace history or shared team knowledge.
- You need to check whether a skill, workflow, or convention already exists.
- You are about to make a product or operating assumption that Saya may know.
- You are about to edit public docs, release notes, runbooks, or prompts that should reflect the team's current decisions.
- You need to distinguish verified team truth from candidate notes or deprecated memory.
- The user asks "what does the team know?", "ask Saya", "ask the team", or a similar workspace-context question.
Don't use when
- The task is fully answerable from the files already in the current workspace.
- The user asks for a general public fact that does not depend on team context.
- The query would require secrets, raw tokens, cross-workspace data, or private information outside the authenticated workspace.
- You need an unapproved write.
saya_actis curated, idempotent, and approval-first.
MCP tools
saya_context(saya.context) — bounded workspace-scoped reads of team knowledge, captured workspace context, decisions, skills, lifecycle status, and trust grades.saya_act(saya.act) — curated, idempotent, approval-firstsave_memory.saya_status(saya.status) — live readiness, auth posture, tool availability, and Convex bridge health for the MCP endpoint.
How to tap well
- Ask a focused question. Prefer "What has this team decided about X?" over "Tell me everything about X."
- Request the strongest truth first: verified decisions, human-reviewed memory, known conventions, then candidate context.
- Carry uncertainty forward. If Saya returns candidate or disputed material, say that in your answer and avoid treating it as production-safe truth.
- Re-query when the task changes. A release note, a code change, and a support reply may need different context slices.
- Use
saya_actonly when the user has clearly asked to save memory or record a decision. Never smuggle credentials, raw tokens, or private cross-workspace data into a write.
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.
- 8d ago First seen · 93 lines · 94 tokens per session scan A 2d1f33db35e7
saya-team-brain is a skill published in the GitHub repository creative-int/saya-plugins (0 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 943 once invoked, about $0.0005 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 skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.