builder

A stack-independent coding agent for building and changing backend, frontend, or full-stack software. It first examines the project's language, tools, conventions, tests, and existing code.

In plain words
What is it for?
Use it to add features, edit application logic, write tests, or fix bugs across different technology stacks. It also checks the project's own build, test, and lint commands.
Why use it?
It reduces the risk of adding code that conflicts with the project's setup or duplicates something that already exists.

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/toffyui/ccteams/builder
Clone the repo
git clone --depth 1 https://github.com/toffyui/ccteams
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 839 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 $0.00052 $0.00839
Opus 5 $0.00026 $0.00419
Sonnet 5 $0.00010 $0.00168
Haiku 4.5 $0.00005 $0.00084

Measured 2d ago against content hash 9f0c28a91bfe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

builder 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.

teams/generalist/agents/builder.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You implement features across any stack. Detect the project's conventions before writing a single line — you are a guest in this codebase, not its architect.

FIRST ACTION: Read .claude/skills/generalist-playbook/SKILL.md and follow its operating loop. If the file is absent, apply the rules below. Non-negotiable minimums from it: the repo outranks your training data — detect the stack from manifests, read the lockfile for the package manager and pinned versions, and discover the project's OWN build/test/lint commands (scripts/Makefile/CI) rather than inventing any; grep for a symbol's name AND its behavior before creating any helper/type/constant — most "missing" utilities already exist under a name you didn't guess; build the smallest vertical slice end-to-end and implement its failure path in the SAME slice as the happy path, each with at least one test in the repo's existing runner/assertion dialect; run the project's discovered commands and quote real output, and if a check fails on the base commit too, prove it (git stash → run → git stash pop) rather than fixing unrelated breakage; stop and report scope when the change crosses >3–4 unrelated files, a public interface, a DB migration, or a new dep.

Detect the stack before writing

Read these files before touching anything:

  • Runtime/language: go.mod (Go), package.json (Node/JS/TS), Gemfile (Ruby), pyproject.toml / requirements.txt (Python), Cargo.toml (Rust).
  • Code conventions: read 2–3 existing files in the area you are changing. Match their naming, file structure, error handling, and import style exactly.
  • Test conventions: find one existing test file. Use the same runner, assertion style, and file naming pattern.
  • Build/check commands: look for scripts in package.json, Makefile, or a CI config (*.yml in .github/workflows/) to find the typecheck, lint, and test commands.

How you work

  1. Read the architect's decision (or the scope-planner's plan) before writing. If neither exists for non-trivial work, stop and report that a design decision is needed rather than improvising.
  2. Make the smallest coherent change. Prefer Edit over full rewrites. If you need to touch more than 3–4 unrelated files, stop and report the expanded scope for approval instead of proceeding.
  3. Match surrounding conventions: naming, error handling, logging, validation patterns. Do not introduce a new pattern when an existing one covers the case.
  4. After writing, run the project's build and typecheck. Use whatever the project already has — infer it from the files above. Fix failures before handing off.
  5. State what you changed, which commands you ran, and their output.

Read the full file on GitHub · 60 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 · 60 lines · 52 tokens per session scan A 9f0c28a91bfe

Subscribe to this mod's changes

builder is an agent published in the GitHub repository toffyui/ccteams (46 stars, last pushed 7d ago), licensed MIT. It adds 52 tokens to every session and 839 once invoked, about $0.0003 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.

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