code-assist

code-assist is a skill for Claude Code, Codex from brazil-bench/pourpoise. It costs 105 tokens per session (7,123 once invoked), scanned A, original, Apache-2.0.

A guided coding process based on test-driven development, or TDD, where tests help define and check the implementation. It follows steps for exploring the code, planning, coding, and committing changes.

In plain words
What is it for?
Implementing a described coding task, refining a rough request, creating test cases, and producing readable code in the project’s language and style.
Why use it?
It helps clarify requirements, fit new code into existing project patterns, and avoid unnecessary complexity.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Implementing a described coding task, refining a rough request, creating test cases, and producing readable code in the project’s language and style.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/brazil-bench/pourpoise/code-assist
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.

Any agent
npx skills add brazil-bench/pourpoise --skill code-assist
Clone the repo
git clone --depth 1 https://github.com/brazil-bench/pourpoise

Made for: Claude Code, 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 code-assist

README.md
[![agentmods](https://agentmods.dev/badge/skills/brazil-bench/pourpoise/code-assist.svg)](https://agentmods.dev/skills/brazil-bench/pourpoise/code-assist)
Your own site
<a href="https://agentmods.dev/skills/brazil-bench/pourpoise/code-assist"><img src="https://agentmods.dev/badge/skills/brazil-bench/pourpoise/code-assist.svg" alt="Measured on agentmods" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,123 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00105 $0.07123
Opus 5 $0.00053 $0.03562
Sonnet 5 $0.00021 $0.01425
Haiku 4.5 $0.00011 $0.00712

Measured 8d ago against content hash 41d68aa62eae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

code-assist scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

let user = try await networkService.fetch(User.self, from: userURL(id))
skills/code-assist/SKILL.md · 763 lines

How it starts

The opening of the file, as written. The whole thing — 763 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Assist

Overview

This sop guides the implementation of code tasks using test-driven development principles, following a structured Explore, Plan, Code, Commit workflow. It balances automation with user collaboration while adhering to existing package patterns and prioritizing readability and extensibility. The agent acts as a Technical Implementation Partner and TDD Coach - providing guidance, generating test cases and implementation code that follows existing patterns, avoids over-engineering, and produces idiomatic, modern code in the target language.

Parameters

  • task_description (required): A description of the task to be implemented. This can be a detailed specification with requirements and acceptance criteria, or even a rough idea that will be refined during the explore and plan phases
  • additional_context (optional): Any supplementary information that would help with understanding the implementation context
  • documentation_dir (optional, default: ".sop/planning"): The directory where planning documents will be stored
  • repo_root (optional, default: current working directory): The root directory of the repository for code implementation
  • task_name (optional): A short, descriptive name for the implementation task
  • mode (optional, default: "auto"): The interaction mode:
    • "interactive": Collaboration with user confirmation at each step
    • "auto": No user interaction after initial setup

Constraints for parameter acquisition:

  • You MUST ask for all parameters upfront in a single prompt, not just required ones because this ensures efficient workflow and prevents repeated interruptions during execution
  • You MUST support multiple input methods for task_description and additional_context (direct input, file path, URL)
  • You MUST normalize mode input to "interactive" or "auto"
  • You MUST validate directory paths and generate task_name if not provided
  • You MUST confirm successful acquisition of all parameters before proceeding
  • If mode is "auto", you MUST warn the user that no further interaction will be required

Read the full file on GitHub · 763 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. 8d ago First seen · 763 lines · 105 tokens per session scan A 41d68aa62eae

Subscribe to this mod's changes

code-assist is a skill published in the GitHub repository brazil-bench/pourpoise (11 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 105 tokens to every session and 7,123 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.