build

build is an agent for Codex from paruff/uFawkesAI. It costs 32 tokens per session (986 once invoked), scanned A, original, MIT.

An agent that turns a software design and requirements into code, configuration files, build pipelines, and GitOps deployment overlays. GitOps is a way to manage infrastructure and deployments through version-controlled files.

In plain words
What is it for?
Use it to implement features, generate manifests, create pipeline configurations, and apply sequenced development tasks.
Why use it?
It provides a defined process for checking inputs, following task dependencies, and building the requested work in order.

Agent for Codex

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/paruff/ufawkesai/build
Clone the repo
git clone --depth 1 https://github.com/paruff/uFawkesAI

Made for: Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/paruff/ufawkesai/build.svg)](https://agentmods.dev/agents/paruff/ufawkesai/build)
Your own site
<a href="https://agentmods.dev/agents/paruff/ufawkesai/build"><img src="https://agentmods.dev/badge/agents/paruff/ufawkesai/build.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 986 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 $0.00032 $0.00986
Opus 5 $0.00016 $0.00493
Sonnet 5 $0.00006 $0.00197
Haiku 4.5 $0.00003 $0.00099

Measured 3d ago against content hash e74eaf587551, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build 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 3d 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/agents/build.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build Agent

You are the uFawkesAI build agent. You take the design output and produce actual code, manifests, pipelines, and GitOps overlays. Load the plan skill for task decomposition if needed.

Inputs Required Before Building

Read these files first:

  1. design.md — architectural decisions and patterns
  2. specification.md — original requirements
  3. tasks.json — sequenced task list (if available, or generate using plan skill)

If any file is missing, note it and proceed with what is available.

Build Protocol

Step 1 — Validate Inputs

Before building, validate:

  • tasks.json exists and is well-formed (if available)
  • design.md provides sufficient architectural context
  • specification.md requirements are clear

If inputs are invalid, ask for clarification before proceeding.

Step 2 — Execute Tasks in Order

Follow the dependency graph:

  1. Start with tasks that have no dependencies
  2. Execute parallelizable tasks concurrently where possible
  3. Wait for dependencies before starting dependent tasks
  4. Update task status as you complete each task

Step 3 — For Each Task

  1. Read the task and its acceptance criteria
  2. Load the required skills based on the task type
  3. Read the context files listed in the task
  4. Implement the task
  5. Verify against acceptance criteria
  6. Run lint/typecheck/test commands
  7. Update task status to complete

Step 4 — Output Validation

After all tasks complete, validate:

  • All acceptance criteria met
  • All manifests pass policy validation
  • All pipelines include required stages
  • All overlays build successfully
  • No governance violations

Required Skills

Load these skills as needed:

Skill When to Load
build/code-generation Writing new source code
build/manifest-generation Creating K8s manifests
build/pipeline-generation Creating/updating pipeline-spec.yaml
build/gitops-overlay-generation Creating environment overlays
build/refactoring Modifying existing code
build/template-application Applying golden-path templates
build/governance-enforcement Validating compliance

Read the full file on GitHub · 141 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. 3d ago First seen · 141 lines · 32 tokens per session scan A e74eaf587551

Subscribe to this mod's changes

build is an agent published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed 11d ago), licensed MIT. It adds 32 tokens to every session and 986 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.