Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Hrithik-Gavankar/brainstacknpx agentmods add skills/hrithik-gavankar/brainstack/team-brainWrote 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/hrithik-gavankar/brainstack/team-brain)<a href="https://agentmods.dev/skills/hrithik-gavankar/brainstack/team-brain"><img src="https://agentmods.dev/badge/skills/hrithik-gavankar/brainstack/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/hrithik-gavankar/brainstack/team-brain"><img src="https://agentmods.dev/badge/skills/hrithik-gavankar/brainstack/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 | $0.00065 | $0.02829 |
| Opus 5.5 | $0.00026 | $0.01132 |
| Sonnet 5.5 | $0.00013 | $0.00566 |
| Haiku 4.5 | $0.00006 | $0.00283 |
Grade A, and why
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 1mo 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Brain — Sync Mode
Part of Brainstack: personal=engineer-brain, crew=team-brain.
| Prefer | Fallback |
|---|---|
MCP start / prepare_research / recall / remember / compliance / peer_notify / correct / history / restore / delete_memory / touch |
bash …/team-brain-api.sh … |
Peer push (#31)
start may attach a Realtime signal listener (bodies still via authenticated pull).
If .team-brain/notify/<KEY>.json updates mid-session, summarize new peer memories before continuing.
If push is unavailable (TEAM_BRAIN_REALTIME=off / no websockets / migration missing), poll/watch/recall still work.
Repo pin (#39) + roles (#40)
- Prefer pinned Jira key from
.team-brain/project.jsonwhen the user omits a key (start/attach). - Never put anon / api_key / invite into the pin — credentials stay gitignored.
whoami.role:viewer→ recall only;member/admin→ remember + delete OK; onlyadminrotates invites /list_members.
Permission tiers
| Role | Read (recall, list, breakdown, history, metrics) | Write (remember, correct, restore, attach) | Delete (delete_memory) |
Admin (rotate invite, set-role, list-members) |
|---|---|---|---|---|
viewer |
✅ | ❌ | ❌ | ❌ |
member |
✅ | ✅ | ✅ | ❌ |
admin |
✅ | ✅ | ✅ | ✅ |
Onboard requires --role member|viewer (admin assigns tier explicitly).
Compliance (policy=stronger_prompts)
v1 follow-up chose stronger prompts + soft session gate (not a hard CLI block).
- Before deep research:
research_okmust be true (startloads context, orprepare_research/recall). - If
sync_status/compliancereturnsagent_action, follow it before coding. - After durable findings:
rememberwithsource_refin the same turn. - Humans may still use the CLI offline; agents must not skip the loop.
- Never upload personal
BRAIN.md.
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.
- 1mo ago Changed · +29 lines 204aae9712a5
- 1mo ago First seen · 243 lines · 65 tokens per session scan A d27a49867f52
team-brain is a skill published in the GitHub repository Hrithik-Gavankar/brainstack (24 stars, last pushed 19d ago), licensed MIT. It adds 65 tokens to every session and 2,829 once invoked, about $0.0003 per session on Opus 5.5. 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
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
kb-memory
Use when knowledge base and memory system for AI agents. Covers company KB, persistent memory, session recall, and brain architecture for context preservation.
context-cycle-proactive
At 80-90% context, save to the brain, route to the right channel, load fresh context, and resume. Built-in lifecycle so every agent stays synced to the second brain and never drops work.
context-agent
Agente de contexto para continuidade entre sessoes. Salva resumos, decisoes, tarefas pendentes e carrega briefing automatico na sessao seguinte.
llm-wiki
Explain and apply the foundational LLM Wiki architecture and knowledge-management strategy. Use for setup, architecture, schema, or organization decisions; operational ingest/query/lint work uses dedicated skills.
wiki-lint
Audit wiki health: broken links, orphans, contradictions, stale content, lifecycle and tag issues. Use for maintenance or health checks. Default is report-only; use wiki-dedup for page-identity merges.