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.
npx skills add brazil-bench/pourpoise --skill code-assistgit clone --depth 1 https://github.com/brazil-bench/pourpoiseWrote 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.
[](https://agentmods.dev/skills/brazil-bench/pourpoise/code-assist)<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>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.
| Model | Per session | Once 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 |
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)) 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
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.
- 8d ago First seen · 763 lines · 105 tokens per session scan A 41d68aa62eae
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.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.