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/activ8-ai/teamwork-mcp/cursorgit clone --depth 1 https://github.com/Activ8-AI/Teamwork-MCPWhat 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 | $0.01073 |
| Opus 5 | $0.00000 | $0.00536 |
| Sonnet 5 | $0.00000 | $0.00215 |
| Haiku 4.5 | $0.00000 | $0.00107 |
Grade A, and why
cursor 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 yesterday.
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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor / Composer Agent Instructions — @vizioz/teamwork-mcp
Charter binding: Activ8 AI Operational Execution & Accountability Charter (v1.5).
Where to look first (context routing)
- This repo’s SSOT map:
docs/SOURCES-OF-TRUTH.md - This repo’s audience + surface contract:
docs/AUDIENCE-SURFACE-CONTRACT.md - Central SSOT map (canonical):
https://github.com/Activ8-AI/activ8-ai-unified-mcp-serveratdocs/SOURCES-OF-TRUTH.md
Output contract
Progress | Evidence | Blockers — no padding.
Minimal working standard
- Prefer reading sources over guessing.
- Keep context tight: store pointers (paths/IDs), fetch details just-in-time.
- Update
memory/MEMORY.mdwhen state changes (Live State + Pending).
Seek-First Planning Gate
- No action begins without a plan.
- Verify in order: Notion first, then repo, then local/runtime files.
- Search for existing artifacts before touching or proposing anything new.
- Build on lineage before create-new.
- For non-trivial work, externalize a short plan with objective, evidence, options, recommendation, and next action.
Seek First to Understand + Verify What Exists
- Seek First to Understand: before answering, deciding, or acting, gather context and ensure full comprehension.
- Verify what exists in Notion: never assume. Check Notion first. Confirm presence, accuracy, and status of relevant information before proceeding.
- Search for existing artifacts: look for relevant databases, pages, prior work, and connected surfaces before touching, modifying, or proposing anything new.
- Build on established work: extend, refine, or elevate what exists. Respect artifact lineage.
- Create new only when necessary: new artifacts or structures only when no suitable reference, structure, or precedent exists.
- Fail closed on deviation: if verification is missing, the user correction changes the path, or drift is detected, stop, surface the mismatch, and restart from verified state.
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.
- yesterday First seen · 92 lines · 0 tokens per session scan A 9ec4f6c80bb6
cursor is an agent published in the GitHub repository Activ8-AI/Teamwork-MCP (0 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,073 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 2026-08-31.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
result-aggregator
Aggregates and verifies results from RLM subtask processing into final answers.
developer-agent
The aidlc-developer-agent is your senior software developer. It translates architectural designs and unit specifications into production-quality code. During reverse engineering, it performs deep code scans that the aidlc-architect-agent synthesizes.