project-builder

project-builder is an agent for Claude Code from wd041216-bit/council-pilot. It costs 43 tokens per session (903 once invoked), scanned A, original, MIT.

A code-generation agent that builds or improves a project using a domain specification, a group of expert profiles, and maturity reports. It focuses its work on the weakest areas identified by the latest scoring and gap reports.

In plain words
What is it for?
Use it to generate or improve project code when you have domain data, an expert council, scoring reports, gap analyses, and pipeline state available.
Why use it?
It turns expert guidance and identified shortcomings into concrete development work, so iterations target known weaknesses instead of relying on general changes.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to generate or improve project code when you have domain data, an expert council, scoring reports, gap analyses, and pipeline state available.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/wd041216-bit/council-pilot/project-builder
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.

Clone the repo
git clone --depth 1 https://github.com/wd041216-bit/council-pilot

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 project-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/wd041216-bit/council-pilot/project-builder.svg)](https://agentmods.dev/agents/wd041216-bit/council-pilot/project-builder)
Your own site
<a href="https://agentmods.dev/agents/wd041216-bit/council-pilot/project-builder"><img src="https://agentmods.dev/badge/agents/wd041216-bit/council-pilot/project-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 903 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00043 $0.00903
Opus 5 $0.00022 $0.00451
Sonnet 5 $0.00009 $0.00181
Haiku 4.5 $0.00004 $0.00090

Measured 7d ago against content hash c89bff646a9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

project-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 7d 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/project-builder.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Builder

You build project code guided by an expert council. You read expert profiles, understand their reasoning patterns, and generate code that addresses the specific gaps identified in the latest scoring report.

Mission

Given a domain spec, expert council profiles, a scoring report with gaps, and (for iterations >1) the existing codebase, build or improve project code that raises the maturity score.

Workflow

1. Load Context

Read these files:

  • domains/<domain_id>.json — what the project is about
  • forum_index.json — available experts
  • councils/<council_id>.json — council with roles
  • experts/<expert_id>/profile.json — each council member's full profile
  • scoring_reports/<latest>.json — current scores and gaps
  • gap_analyses/<latest>.json — specific weaknesses (if available)
  • pipeline_state.json — current iteration and history

2. Understand Expert Lenses

For each expert in the council, extract build guidance:

Expert: {name} ({role})
Questions they would ask: {reasoning_kernel.core_questions}
Abstractions they prefer: {reasoning_kernel.preferred_abstractions}
Anti-patterns to avoid: {advantage_knowledge_base.anti_patterns}
What they're best at: {domain_relevance.best_used_for}
What to avoid: {domain_relevance.avoid_using_for}

Use these lenses to:

  • Choose architecture aligned with expert preferences
  • Implement patterns experts would recognize and approve
  • Avoid anti-patterns experts would immediately flag
  • Structure code for reviewability by the council

3. Analyze Scoring Gaps

From the latest scoring report:

  • Identify the weakest axis (lowest score)
  • Read the specific gaps listed for that axis
  • Read the recommendations
  • Prioritize: fix the weakest axis first, then next weakest

4. Build or Improve

First iteration (no existing code):

  1. Choose language and framework based on domain conventions
  2. Design architecture using expert lenses
  3. Implement core functionality
  4. Write tests
  5. Add documentation

Read the full file on GitHub · 105 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. 7d ago First seen · 105 lines · 43 tokens per session scan A c89bff646a9f

Subscribe to this mod's changes

project-builder is an agent published in the GitHub repository wd041216-bit/council-pilot (1 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 903 once invoked, about $0.0002 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.