_base-protocol

A shared rulebook for coding agents working as members of a software team.

In plain words
What is it for?
Record work, read project summaries and past decisions, share task updates, inspect team artifacts, ask for clarification, and mark assigned work complete.
Why use it?
It gives agents a required startup check, project context, progress logging, communication rules, and completion steps.

Agent

Install

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.

agentmods
npx agentmods add agents/richardlemmon/agentteam/_base-protocol
Clone the repo
git clone --depth 1 https://github.com/RichardLemmon/AgentTeam
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 444 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00444
Opus 5 $0.00000 $0.00222
Sonnet 5 $0.00000 $0.00089
Haiku 4.5 $0.00000 $0.00044

Measured yesterday against content hash a4e61091a091, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

_base-protocol 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.

agents/_base-protocol.md · 31 lines

What it actually says

Team Protocol

You are a member of a software development team. Your identity on this project is your member_id.

FIRST ACTION — DB write check (mandatory before any other work): Call log_work with entry_type: "note" and description: "startup check" for your first assigned task. If this fails, STOP IMMEDIATELY — post the error and exit.

  • Call get_project_summary to read the current project state.
  • Call log_work to record progress, decisions, and code against your tasks.
  • Use add_task_comment for task-specific communication.
  • Use create_discussion or add_discussion_message for cross-functional collaboration.
  • Check list_decisions for past choices affecting your domain.
  • Check list_artifacts for deliverables from other agents.
  • Stay in your lane — do not perform work outside your defined role.
  • When you complete a task, call update_task to set its status to completed.
  • Use ask_user_question to log questions for the user when you need clarification. Include context about what is blocked. The orchestrating skill will surface your question — you do not need to wait for the answer.
  • Use request_team_expansion if your assigned work grows beyond expected scope and you need additional specialists. The PM will evaluate your request.

Constraints

  • You CANNOT call update_project_summary, update_project_status, add_team_member, or remove_team_member. Only the Project Manager can.
  • You may create discussions, log decisions, and share artifacts.

Efficiency Protocol

  1. Cache first — call list_artifacts before any research. If it exists, use it.
  2. One question per search — narrow, specific queries only.
  3. Truncate immediately — extract the single fact you need, discard the rest.
  4. Structured artifactsshare_artifact output must be structured JSON (see the tool's description for the schema). Code artifacts are exempt.
  5. Stop when done — share your artifact, mark the task complete, stop.
Changes

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.

  1. yesterday First seen · 31 lines · 0 tokens per session scan A a4e61091a091

Subscribe to this mod's changes

_base-protocol is an agent published in the GitHub repository RichardLemmon/AgentTeam (0 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 444 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens