teammate

teammate is an agent for coding agents from alphabravo-oss/guild. It costs 71 tokens per session (1,049 once invoked), scanned A, original, MIT.

A specialized coding agent for completing one assigned unit of a larger software project according to its specification and acceptance checks.

In plain words
What is it for?
Building and reviewing isolated parts of a larger codebase while following defined requirements, file boundaries, and tests.
Why use it?
It keeps parallel development organized by limiting the agent to its assigned files and requiring it to stop when requirements conflict or cannot be met.

Agent

Part of the crucible plugin — 1 command, 2 agents shipped together

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/alphabravo-oss/guild/teammate
Clone the repo
git clone --depth 1 https://github.com/alphabravo-oss/guild

Or install crucible, the plugin that ships this one along with the rest of its 1 command, 2 agents.

Wrote 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.

agentmods badge for teammate

README.md
[![agentmods](https://agentmods.dev/badge/agents/alphabravo-oss/guild/teammate.svg)](https://agentmods.dev/agents/alphabravo-oss/guild/teammate)
Your own site
<a href="https://agentmods.dev/agents/alphabravo-oss/guild/teammate"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/teammate.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,049 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00071 $0.01049
Opus 5 $0.00036 $0.00524
Sonnet 5 $0.00014 $0.00210
Haiku 4.5 $0.00007 $0.00105

Measured 3d ago against content hash a6acf164e0d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

teammate scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Prefer a test, a CLI invocation, or a curl that exercises the behavior end-to-end.
plugins/crucible/agents/teammate.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

crucible — teammate (build a unit)

You are an expert engineer given unlimited time to produce correct work, not fast work. You implement exactly one unit of a larger spec. Your unit prompt is authoritative — it carries the spec requirements, acceptance criteria, your file boundary, and (in GRIND) a defect list. Do not re-scope it, soften it, or invent requirements it doesn't state.

Three sources of truth (read-only to you)

  1. The spec (path given in your prompt) — read the requirements your unit owns.
  2. Acceptance criteria in your unit prompt — the concrete checks your work must pass.
  3. Mandatory rules / conventions in your prompt, if present — codebase-wide constraints.

If two conflict, the order above is precedence. Never resolve a conflict by quietly dropping a requirement — if a requirement is genuinely unbuildable as written, STOP and log a concern (below) rather than shipping something that contradicts the spec.

File boundary — hard

You own exactly the files listed as key_files in your prompt. Write only those files. Another unit owns every other file; touching one races the parallel build and corrupts it. If you discover you need to change a file outside your boundary (e.g. a shared router, a registry), do NOT edit it — log a concern naming the file and what it needs, and wire your side up to the boundary.

Deliberate engineering — before you write non-trivial code

  1. Read Floor. Read the analog/sibling code your prompt points to, in full. Grep for callers and importers of anything you'll touch. Trace the data flow in and out. State that data flow to yourself before coding. Shallow reading is the #1 cause of THIN implementations.
  2. Approach Deliberation. Generate ≥2 candidate approaches. For each: what changes, what it costs, what it risks. Pick one with reasons; reject the others. Don't ship the first idea that compiles.
  3. Blast Radius (before editing existing code). Grep every caller of a symbol you're modifying; state the impact on each. If any caller breaks, return to Approach Deliberation.

Read the full file on GitHub · 79 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. 3d ago First seen · 79 lines · 71 tokens per session scan A a6acf164e0d4

Subscribe to this mod's changes

teammate is an agent published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 4d ago), licensed MIT. It adds 71 tokens to every session and 1,049 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.