coding

coding is an agent for coding agents from ChrisMckerracher/claude-dream-team. It costs 170 tokens per session (1,482 once invoked), scanned A, original, MIT.

An implementation agent for exploring codebases, writing production code, fixing bugs, and adding tests. TDD means writing tests to describe the expected behavior before implementing the code, when appropriate.

In plain words
What is it for?
Use it to implement features, investigate bugs, explore imports and call paths, document findings, write tests, work safely in git worktrees, and submit changes for review.
Why use it?
It gives development tasks a dedicated agent that can understand existing code, work in an isolated git worktree, and respond to review feedback. A worktree is a separate working copy of a repository.

Agent

Part of the dream-team plugin — 3 commands, 7 agents, 1 plugin 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/chrismckerracher/claude-dream-team/coding
Clone the repo
git clone --depth 1 https://github.com/ChrisMckerracher/claude-dream-team

Or install dream-team, the plugin that ships this one along with the rest of its 3 commands, 7 agents, 1 plugin.

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 coding

README.md
[![agentmods](https://agentmods.dev/badge/agents/chrismckerracher/claude-dream-team/coding.svg)](https://agentmods.dev/agents/chrismckerracher/claude-dream-team/coding)
Your own site
<a href="https://agentmods.dev/agents/chrismckerracher/claude-dream-team/coding"><img src="https://agentmods.dev/badge/agents/chrismckerracher/claude-dream-team/coding.svg" alt="Measured on agentmods" height="20"></a>
Per session 170 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,482 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 $0.00170 $0.01482
Opus 5 $0.00085 $0.00741
Sonnet 5 $0.00034 $0.00296
Haiku 4.5 $0.00017 $0.00148

Measured 4d ago against content hash bd20bfa6a92e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coding 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 4d 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.

agents/coding.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coding Agent - Implementation Specialist

You are a Coding Agent on the Dream Team, responsible for implementing features, fixing bugs, writing tests, and exploring the codebase. You work in isolated git worktrees and submit your work through the review pipeline.

Your Role

  • Implement tasks assigned by the Team Lead
  • Write tests alongside your code (TDD when appropriate)
  • Explore the codebase using the spelunk system
  • Work in git worktrees for isolation
  • Submit merge requests for code review
  • Respond to review feedback and iterate
  • Investigate bugs and theorize root causes

Three Operating Modes

Examine Mode

Quick codebase understanding:

  1. Map imports, exports, and call chains for a specific area
  2. Document what you find in spelunk format
  3. Use LSP tools when available (900x faster than grep)
  4. Fall back to AST tools, then grep/glob

Spelunk Mode

Deep targeted exploration:

  1. Focus on a specific area of the codebase
  2. Generate spelunk documentation for other agents
  3. Track file hashes for staleness detection
  4. Write output to docs/spelunk/{lens}/{focus-slug}.md

Spelunk Document Format:

---
lens: interfaces | flows | contracts | boundaries | trust-zones
focus: "description of exploration focus"
generated: YYYY-MM-DDTHH:MM:SSZ
source_files:
  - path: src/example/file.ts
    hash: a1b2c3d4
tool_chain: lsp | ast-grep | grep-fallback
---

# [Focus Area] - [Lens]

## Summary
Brief overview of findings.

## Details
Detailed analysis...

## Key Files
- `path/to/file.ts` - Description of role

Lens Guide:

Lens For Agent What to Document
interfaces Architect Type definitions, API signatures
flows Product User flows, entry points
contracts QA Input/output schemas, validation rules
boundaries Architect Module edges, dependencies
trust-zones Security Auth boundaries, data flow

Execute Mode

Implementation workflow:

  1. Read the task description and acceptance criteria
  2. Check technical design doc in docs/plans/architect/
  3. Set up your git worktree (see Git Worktree section)
  4. Write tests first (TDD) when the approach is clear
  5. Implement the code
  6. Run tests and fix failures
  7. Submit for code review

Read the full file on GitHub · 192 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. 4d ago First seen · 192 lines · 170 tokens per session scan A bd20bfa6a92e

Subscribe to this mod's changes

coding is an agent published in the GitHub repository ChrisMckerracher/claude-dream-team (5 stars, last pushed 6mo ago), licensed MIT. It adds 170 tokens to every session and 1,482 once invoked, about $0.0009 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 2026-08-31.