PROTOCOL

A communication protocol for Specflow agents working as a team, including direct messages, broadcasts, and a shared task list. It explains how these messages map to Claude Code's teammate tools.

In plain words
What is it for?
Use it when running Specflow work in Agent Teams mode, such as sending requests to another teammate, notifying the team about files, or managing shared tasks.
Why use it?
It gives agents a common way to coordinate work, share file ownership, track dependencies, and avoid conflicting changes.

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/hulupeep/specflow/protocol
Clone the repo
git clone --depth 1 https://github.com/Hulupeep/Specflow
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 1,734 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 $0.01734
Opus 5 $0.00000 $0.00867
Sonnet 5 $0.00000 $0.00347
Haiku 4.5 $0.00000 $0.00173

Measured yesterday against content hash 8dc601a46e7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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/PROTOCOL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Communication Protocol

Overview

This protocol defines how Specflow agents communicate in Agent Teams mode. It maps Specflow's logical message types to Claude Code's TeammateTool API.

Agent Teams is the default execution model. Detection is automatic:

  • TeammateTool available (Claude Code 4.6+) → Agent Teams mode
  • TeammateTool unavailable → fall back to Task tool subagents with no inter-agent messaging

No environment variable is needed.

Claude Code TeammateTool API

Agent Teams uses three communication mechanisms:

1. Direct Messages (write operation)

Send a message to one specific teammate by name.

TeammateTool(operation: "write", to: "db-coordinator", message: "REQUEST_MIGRATION #50 tables:[users, sessions]")

2. Broadcast (broadcast operation)

Send a message to ALL teammates. Use sparingly — costs scale with team size.

TeammateTool(operation: "broadcast", message: "TOUCHING_FILE src/lib/auth.ts")

3. Shared Task List (TaskCreate / TaskUpdate / TaskList)

All teammates share a task list with dependency tracking. Tasks auto-unblock when dependencies complete. File-locking prevents race conditions on claims.

Environment Variables (set automatically on each teammate)

CLAUDE_CODE_TEAM_NAME       # Team identifier (mythic name, e.g., "Fianna")
CLAUDE_CODE_AGENT_ID        # Unique agent session ID
CLAUDE_CODE_AGENT_NAME      # Human-readable name (mythic name, e.g., "Yeats")
CLAUDE_CODE_AGENT_TYPE      # Role (functional, e.g., "issue-lifecycle")
CLAUDE_CODE_PARENT_SESSION_ID  # Lead session that spawned this agent

Team Naming

Agent Teams uses mythic Irish names instead of functional IDs. This makes completion messages memorable without affecting behavior.

  • Team names (CLAUDE_CODE_TEAM_NAME): Fianna, Tuatha, Red Branch, Brigid's Forge, Tir na nOg
  • Agent names (CLAUDE_CODE_AGENT_NAME): Yeats, Swift, Goibniu, Hamilton, Keane, etc.
  • Agent types (CLAUDE_CODE_AGENT_TYPE): Still functional (issue-lifecycle, db-coordinator, etc.)

Read the full file on GitHub · 174 lines

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 · 174 lines · 0 tokens per session scan A 8dc601a46e7f

Subscribe to this mod's changes

PROTOCOL is an agent published in the GitHub repository Hulupeep/Specflow (24 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,734 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.

Related

Other agents, from other repositories

compliance-auditor

Comprehensive SDLC compliance auditor that reviews projects against all standards. Use PROACTIVELY when the user asks to "audit compliance", "check SDLC requirements", "review project standards", "validate compliance", or wants a full assessment of how well a project meets SDLC requirements.

zircote-plugins/sdlc-quality · 57 tokens

quality-enforcer

Code quality specialist enforcing formatting, linting, error handling, and documentation standards. Use PROACTIVELY when the user asks to "check code quality", "review formatting", "enforce lint rules", "fix code style", or needs code quality assessment and remediation.

zircote-plugins/sdlc-quality · 54 tokens

security-reviewer

Security-focused reviewer specializing in vulnerability assessment, supply chain security, and secure coding practices. Use PROACTIVELY when the user asks to "review security", "audit dependencies", "check for vulnerabilities", "security scan", or needs security-specific compliance assessment.

zircote-plugins/sdlc-quality · 51 tokens

task-executor

Use this agent to monitor or debug autonomous task execution. Examples - "Why did my task fail?", "Show me the output from the last task run", "Check if the taskrunner is still running".

Stackbilt-dev/cc-taskrunner · 45 tokens

code-reviewer

Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions. Merges security review capabilities including OWASP validation, secrets scanning, and regression detection. Uses confidence-based filtering for quality issues and severity classification for…

zircote-plugins/refactor · 65 tokens

changelog-updater

Updates CHANGELOG.md following Keep a Changelog conventions based on staged changes.

TheSmuks/ai-project-template · 20 tokens