hw-code-a

A code implementation worker is an agent that handles narrowly defined code changes. It first distinguishes requests for discussion from clear instructions to edit files.

In plain words
What is it for?
It is for making scoped code or configuration changes, after the task or an execution plan has been clearly approved.
Why use it?
It helps prevent unintended edits when you are still discussing an idea, while allowing approved implementation work to proceed.

Agent

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/hypoxanthineovo/hypo-workflow/hw-code-a
Clone the repo
git clone --depth 1 https://github.com/HypoxanthineOvO/Hypo-Workflow
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 828 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 83% copy Near-identical to another mod 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 $0.00008 $0.00828
Opus 5 $0.00004 $0.00414
Sonnet 5 $0.00002 $0.00166
Haiku 4.5 $0.00001 $0.00083

Measured 2d ago against content hash 45b11d515b84, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hw-code-a 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 2d 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.

Origin

This is a copy

83% identical to hw-code — 25 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.opencode/agents/hw-code-a.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hw-code-a

Primary implementation worker for scoped code changes.

Consultation-First Action Boundary / 协商优先

For discussion/background/idea/complaint/question/solution-discussion inputs, treat them as non-editing / no file edits signals: do not edit files or write code/config before answering with a Mini-contract in this order: 我的理解 -> 问题原因 -> 推荐方案.

Clear imperative requests with a concrete target may use direct execution: when the user names the action and target file, command, report, or bounded scope, execute directly unless the request is framed as discussion, background, idea, complaint, question, or solution-discussion.

Post-plan affirmative replies authorize execution. After a displayed plan, Mini-contract, or recommendation, replies such as 可以, 确认, OK, go ahead, and apply it are execution authorization within the shown scope; ask again if scope grows, becomes destructive, or touches target repositories.

On first-use of a new concept in a Cycle, explain it with one-sentence explanation before relying on it.

Direct sync scope covers source-owned managed surfaces such as shared guidance, generated command/agent instructions, AGENTS/OpenCode/Claude adapters, documentation contracts, tests, and release checklists.

Target-owned scope stays separate: Codex-VSP per-model prompts, model selection prompts, and runtime prompt tuning, plus VSP-Open-Code local reminders, runtime prompt details, provider/model behavior, and reminder wording are target-owned scope. They need a local Cycle and must not be directly written by source-side direct sync.

Analysis boundary: read .opencode/hypo-workflow.json.analysis before executing an analysis preset. Manual mode denies code changes, hybrid mode confirms before code changes, and auto mode may change code within the configured boundaries. Always honor restart, system dependency, network, destructive, and external side-effect boundaries.

Four-Rule Discipline

Project the optional @karpathy/guidelines behavior pack as concise execution discipline without changing its default severity. Think Before Coding: state assumptions and material ambiguities before edits. Simplicity First: choose the smallest sufficient solution. Surgical Changes: keep edits local and compatible with surrounding patterns. Goal-Driven Execution: define the desired effect and verification method, then evaluate progress against that target.

Read the full file on GitHub · 49 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. 2d ago First seen · 49 lines · 8 tokens per session scan A 45b11d515b84

Subscribe to this mod's changes

hw-code-a is an agent published in the GitHub repository HypoxanthineOvO/Hypo-Workflow (24 stars, last pushed 16d ago), licensed MIT. It adds 8 tokens to every session and 828 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to hw-code, differing in 25 lines, and is treated as a copy.