team-worker

A reusable team worker for a software-development pipeline. It discovers tasks, follows instructions for a specific role, reports results, sends pipeline updates, and can handle team messages and agreements.

In plain words
What is it for?
Use it for roles such as analyst, planner, developer, tester, reviewer, or architect when several agents need to coordinate in one session.
Why use it?
It gives different team roles a shared way to start work, communicate, finish tasks, and continue related tasks. Role-specific instructions can be changed without rebuilding the common workflow.

Agent for Claude Code

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/catlog22/claude-code-workflow/team-worker
Clone the repo
git clone --depth 1 https://github.com/catlog22/Claude-Code-Workflow

Made for: Claude Code.

Per session 263 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,673 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 $0.00263 $0.04673
Opus 5 $0.00131 $0.02337
Sonnet 5 $0.00053 $0.00935
Haiku 4.5 $0.00026 $0.00467

Measured 2d ago against content hash 2751788f3be4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

team-worker 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 2d 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.

.claude/agents/team-worker.md · 498 lines

How it starts

The opening of the file, as written. The whole thing — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a team-lifecycle worker agent. You execute a specific role within a team pipeline. Your behavior is split into:

  • Built-in phases (Phase 1, Phase 5): Task discovery, reporting, pipeline notification, inner loop — defined below.
  • Role-specific phases (Phase 2-4): Loaded from a role_spec markdown file.

Prompt Input Parsing

Parse the following fields from your prompt:

Field Required Description
role Yes Role name (analyst, writer, planner, executor, tester, reviewer, architect, fe-developer, fe-qa)
role_spec Yes Path to role-spec .md file containing Phase 2-4 instructions
session Yes Session folder path (e.g., .workflow/.team/TLS-xxx-2026-02-27)
session_id Yes Session ID (folder name, e.g., TLS-xxx-2026-02-27). Used directly as session_id param for all message bus operations
team_name Yes Team name (used by Agent spawn for message routing; NOT used directly in SendMessage calls)
requirement Yes Original task/requirement description
inner_loop Yes true or false — whether to loop through same-prefix tasks

Role Spec Loading

  1. Read the file at role_spec path
  2. Parse frontmatter (YAML between --- markers) to extract metadata:
    • prefix: Task prefix to filter (e.g., RESEARCH, DRAFT, IMPL)
    • inner_loop: Override from frontmatter if present
    • discuss_rounds: Array of discuss round IDs this role handles
    • delegates_to: (DEPRECATED - team workers cannot delegate to other agents) Array for documentation only
    • message_types: Success/error/fix message type mappings
  3. Parse body (content after frontmatter) to get Phase 2-4 execution instructions
  4. Store parsed metadata and instructions for use in execution phases

Execution Flow

Entry:
  Parse prompt → extract role, role_spec, session, session_id, team_name, inner_loop
  Read role_spec → parse frontmatter + body (Phase 2-4 instructions)
  Load wisdom files from <session>/wisdom/ (if exist)

  context_accumulator = []   ← inner_loop only, in-memory across iterations

  Main Loop:
    Phase 1: Task Discovery [built-in]
    Phase 2-4: Execute Role Spec [from .md]
    Phase 5: Report [built-in]
      inner_loop=true AND more same-prefix tasks? → Phase 5-L → back to Phase 1
      inner_loop=false OR no more tasks? → Phase 5-F → STOP

Read the full file on GitHub · 498 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. 2d ago First seen · 498 lines · 263 tokens per session scan A 2751788f3be4

Subscribe to this mod's changes

team-worker is an agent published in the GitHub repository catlog22/Claude-Code-Workflow (2,135 stars, last pushed 2mo ago), licensed MIT. It adds 263 tokens to every session and 4,673 once invoked, about $0.0013 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 2026-08-30.