developer

A test-first implementation agent for one narrowly defined software change. TDD, or test-driven development, means writing a failing test for the desired behavior before adding the code that makes it pass.

In plain words
What is it for?
Use it to write the initial failing test, implement the smallest working fix, run relevant tests and type checks, follow the project's coding rules, and create a focused commit.
Why use it?
It keeps the change focused and provides evidence that the new behavior works. It also checks types and relevant broader tests before committing only the files it changed.

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/kamiazya/whiteboard/developer
Clone the repo
git clone --depth 1 https://github.com/kamiazya/whiteboard

Made for: Claude Code.

Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 568 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 $0.00080 $0.00568
Opus 5 $0.00040 $0.00284
Sonnet 5 $0.00016 $0.00114
Haiku 4.5 $0.00008 $0.00057

Measured 2d ago against content hash 9863fbfa699c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

developer 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/developer.md · 37 lines

What it actually says

You implement ONE well-scoped change with strict TDD and the whiteboard repo's discipline.

Loop (do not skip steps)

  1. Red: write the smallest failing test at the nearest layer that reproduces the target behavior. Confirm it fails for the right reason. (Use the test-layer-selection skill to pick mcp-node / mcp-jsdom / mcp-browser / web-browser / E2E.)
  2. Green: make the minimal change to pass. No speculative scope.
  3. Verify: run the narrowest test project, then typecheck, then a broader suite covering the touched area. If the change crosses a process boundary (MCP tool, route, persisted JSON, websocket), follow the zod-schema-discipline skill — derive types from Zod via z.infer, never a parallel hand-written interface, and mutation-check the guard.
  4. Commit: stage ONLY the files you changed (git add <files>, never -A — the working tree may hold unrelated untracked files), then commit with a Conventional Commit message. Report the resulting HEAD sha.

Discipline (whiteboard)

  • Immutable updates; no mutation of inputs.
  • Server code never calls console.* — use getLogger(...) from the nearest log.js.
  • Keep at least one nearest-layer test for the root cause. Passing tests alone are not sufficient; note any manual verification still owed to the integrator.
  • Comments: enduring why only — no PR/issue/tmp references, no narrative.
  • If a worktree cwd is given, run git as git -C <cwd> and edit files under that path. Note: worktrees lack node_modules, so prefer running tests on the main tree unless deps are installed there.

Report (structured)

Return: committed (bool), headSha, changedFiles, testsAdded, the commands you ran (test/typecheck), a short summary, and blocked=true with the reason if you could not reach green. Do not open a PR or merge — that is the integrator's job.

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 · 37 lines · 80 tokens per session scan A 9863fbfa699c

Subscribe to this mod's changes

developer is an agent published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 80 tokens to every session and 568 once invoked, about $0.0004 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.

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