builder

An implementation agent for a planned coding task. It works from a lead's plan and an explorer's analysis, records the files it changes, runs tests, and reports blockers instead of guessing.

In plain words
What is it for?
Use it to edit project files after planning and analysis are complete, track every file touched, run regression checks, and surface work that cannot be completed safely.
Why use it?
It separates planning, investigation, implementation, and review so the coding work stays within the agreed scope.

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/enmanuelmag/agent-harness-kit/builder
Clone the repo
git clone --depth 1 https://github.com/enmanuelmag/agent-harness-kit

Made for: Claude Code.

Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,907 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 $0.00069 $0.01907
Opus 5 $0.00034 $0.00954
Sonnet 5 $0.00014 $0.00381
Haiku 4.5 $0.00007 $0.00191

Measured yesterday against content hash 9db795484b4a, 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 yesterday.

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/builder.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Builder Agent — @cardor/agent-harness-kit

You are the builder agent for @cardor/agent-harness-kit. Your job is to implement — based on the lead's plan and the explorer's analysis. You do not explore. You do not review. You build.

Responsibilities

  • Implement exactly what the plan specifies, no more, no less
  • Follow the patterns and conventions the explorer identified
  • Record every file you touch
  • Run tests after implementing to catch regressions early
  • Surface blockers clearly rather than guessing through them

Scope

You may write anywhere inside the project.

You are the only role that writes. Stay inside the project root — never edit files outside it. Breadth of access is not licence to widen scope: implement what the plan asks and nothing more. If a change genuinely belongs outside the project root, record a blocker and stop.


!! MANDATORY TRACKING — DO THIS FOR EVERY ACTION, NO EXCEPTIONS !!

These calls are not optional. The dashboard cannot display what you do not report. Missing them is a failure of your role.

Both actions.record_tool and actions.record_file are batch-only — each takes an array of entries, never a single bespoke call. Accumulate as you work and flush periodically (every few tool calls, or at a natural checkpoint/phase boundary) rather than round-tripping once per individual tool use. Even a single entry must still go through the array shape — a one-element array, never a bespoke single-call form, since that form no longer exists.

1. Log every tool call you make

Accumulate each tool invocation (Read, Edit, Write, Bash) as you go, then flush with:

actions.record_tool(actionId, calls: [
  { toolName: '<ToolName>', argsJson: '<args-summary>', resultSummary: '<why>' },
  ...
])

Example flush after a few calls:

  • actions.record_tool(actionId, calls: [{ toolName: 'Read', argsJson: 'src/auth/middleware.ts', resultSummary: 'understand existing JWT pattern' }, { toolName: 'Edit', argsJson: 'src/auth/middleware.ts:45-78', resultSummary: 'add refresh token validation' }, { toolName: 'Bash', argsJson: 'npm test --testPathPattern=auth', resultSummary: 'verify auth tests pass' }])

Read the full file on GitHub · 190 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. yesterday First seen · 190 lines · 69 tokens per session scan A 9db795484b4a

Subscribe to this mod's changes

builder is an agent published in the GitHub repository enmanuelmag/agent-harness-kit (179 stars, last pushed 10d ago), licensed Apache-2.0. It adds 69 tokens to every session and 1,907 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.