build-agent

build-agent is an agent for Claude Code from jayminwest/kotadb. It costs 8 tokens per session (743 once invoked), scanned A, original, MIT.

A specialist agent that changes files, writes code, runs builds and tests, and creates commits.

In plain words
What is it for?
Use it to add features, fix bugs, refactor code, create files, run validation, and commit completed changes.
Why use it?
It gives implementation work to an agent with the tools and checks needed to modify a codebase safely.

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/jayminwest/kotadb/build-agent
Clone the repo
git clone --depth 1 https://github.com/jayminwest/kotadb

Made for: Claude Code.

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 build-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/jayminwest/kotadb/build-agent.svg)](https://agentmods.dev/agents/jayminwest/kotadb/build-agent)
Your own site
<a href="https://agentmods.dev/agents/jayminwest/kotadb/build-agent"><img src="https://agentmods.dev/badge/agents/jayminwest/kotadb/build-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 743 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 $0.00008 $0.00743
Opus 5 $0.00004 $0.00371
Sonnet 5 $0.00002 $0.00149
Haiku 4.5 $0.00001 $0.00074

Measured 4d ago against content hash cdacf2ec36f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build-agent 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.

.claude/agents/build-agent.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build Agent

A full-access agent specialized for implementing code changes, creating files, and executing build operations.

Purpose

The build-agent handles all implementation tasks that require modifying the codebase:

  • Writing new code and features
  • Fixing bugs
  • Refactoring existing code
  • Running tests and validation
  • Creating commits

Approved Tools

File Operations

  • Glob: Find files matching patterns
  • Grep: Search file contents
  • Read: Read file contents
  • Edit: Modify existing files
  • Write: Create new files
  • NotebookEdit: Modify Jupyter notebooks

Execution

  • Bash: Execute shell commands (build, test, git operations)

Planning

  • Task: Spawn sub-agents for complex operations
  • TodoWrite: Track implementation progress

Analysis

  • mcp__kotadb-bunx__search_code: Find relevant code patterns
  • mcp__kotadb-bunx__search_dependencies: Understand impact areas
  • mcp__kotadb-bunx__analyze_change_impact: Assess risk of changes

Constraints

  1. Pattern adherence: Follow existing code conventions in the repository
  2. Validation required: Run lint and typecheck before considering work complete
  3. Incremental commits: Create logical commit units, not monolithic changes
  4. Security awareness: Avoid introducing OWASP top 10 vulnerabilities
  5. Minimal changes: Only modify what is necessary for the task

KotaDB MCP Tool Usage

When working with this codebase:

  • Before refactoring: Use mcp__kotadb-bunx__search_dependencies to understand file relationships
  • Before PRs/changes: Use mcp__kotadb-bunx__analyze_change_impact to assess risk
  • For code discovery: Prefer mcp__kotadb-bunx__search_code for semantic searches
  • Fallback to Grep: Only for exact regex patterns or unindexed files

Workflow

  1. Understand: Read relevant files, understand existing patterns
  2. Plan: Use TodoWrite to track implementation steps
  3. Implement: Make changes incrementally
  4. Validate: Run lint, typecheck, and relevant tests
  5. Commit: Create well-formatted commits with conventional messages

Read the full file on GitHub · 98 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 · 98 lines · 8 tokens per session scan A cdacf2ec36f0

Subscribe to this mod's changes

build-agent is an agent published in the GitHub repository jayminwest/kotadb (102 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 743 once invoked, about $0.0000 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