ho-design

ho-design is a skill for Codex from hf745316389/ho-codeflow. It costs 51 tokens per session (1,534 once invoked), scanned A, original, Apache-2.0.

A planning workflow that produces a written software design before coding begins. It records the project's current behavior, the proposed change, and questions that must be answered first.

In plain words
What is it for?
Use it to investigate a proposed change, document affected files and tests, define acceptance criteria, and identify blocking open questions.
Why use it?
It prevents coding against an unclear request or making business decisions that have not been agreed on. The design can also guide another developer or agent in a later session.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md.

Good fit Use it to investigate a proposed change, document affected files and tests, define acceptance criteria, and identify blocking open questions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hf745316389/ho-codeflow/ho-design
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 hf745316389/ho-codeflow --skill ho-design
Clone the repo
git clone --depth 1 https://github.com/hf745316389/ho-codeflow

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 ho-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/hf745316389/ho-codeflow/ho-design/github.svg)](https://agentmods.dev/skills/hf745316389/ho-codeflow/ho-design)
Your own site
<a href="https://agentmods.dev/skills/hf745316389/ho-codeflow/ho-design"><img src="https://agentmods.dev/badge/skills/hf745316389/ho-codeflow/ho-design/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ho-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/hf745316389/ho-codeflow/ho-design"><img src="https://agentmods.dev/badge/skills/hf745316389/ho-codeflow/ho-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,534 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 $0.00051 $0.01534
Opus 5 $0.00026 $0.00767
Sonnet 5 $0.00010 $0.00307
Haiku 4.5 $0.00005 $0.00153

Measured 8d ago against content hash ffa8d3caa340, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ho-design 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 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.

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.

skills/ho-design/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design

Produce one file someone else can implement from with no access to this conversation. You do not write business code in this phase.

Locate the change

Read the project's own rules first — AGENTS.md, or whatever equivalent instruction file your host reads — then .ho/protocol.md and .ho/config.yaml if they exist. Change artifacts live in .ho/changes/<id>/.

If more than one change is open and the request names none of them, list the candidates and ask which. Do not pick one, and do not do all of them.

Settle the facts yourself

File paths, function signatures, test commands, current behaviour: open the files and read them. Never hand back a question you could have answered by reading the project.

Questions that block

A question whose answer changes the direction of the work stops this phase. Write the design down to that point, put the question in Open questions, and stop. One question at a time — the one that changes the most.

Reversibility is not a reason to answer it yourself.

Rationalization Why it fails
"It's additive and reversible, so I'll pick one and flag it" Reversible describes the code. The question is about what the number means. A wrong meaning gets acted on before anyone reverts anything.
"No reply is possible in this run, so I have to decide" Not being able to get an answer now is the reason to write the question down, not the reason to answer it.
"The other reading already exists elsewhere, so they obviously meant this one" That is an inference about intent. It is still a guess.
"I'll implement it and flag the ambiguity in my report" Disclosure afterwards is not a decision the user made.
"Asking would block them on something trivial" If it were trivial it would not change the direction.

Red flags — you are about to fail: "I'll pick the reversible one and note it" · "it's additive, nothing breaks" · "I'll flag it in the report" · "there's nobody to ask right now" · "they must mean this one".

Read the full file on GitHub · 140 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 140 lines · 51 tokens per session scan A ffa8d3caa340

Subscribe to this mod's changes

ho-design is a skill published in the GitHub repository hf745316389/ho-codeflow (4 stars, last pushed 26d ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,534 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

agent-orchestrator-v2

Agent Orchestrator workflow skill. Use this skill when the user needs Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management and the operator should preserve the upstream workflow, copied support files, and…

diegosouzapw/awesome-omni-skills · 77 tokens

Subagent Driven Development

Orchestrate specialized, autonomous AI agents to execute parallel subtasks with strict boundaries.

ankur-gaurav161418/omniforge · 22 tokens

Cursor Workflow Optimizer

Master Cursor IDE with optimal configurations, custom rules, MCP integrations, and workflow patterns that 10x developer productivity.

demo112/yunqu-ai-skills · 28 tokens

agent-orchestrator

Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.

sinhoneyy/master-skills · 41 tokens

agent-orchestrator

Agent Orchestrator workflow skill. Use this skill when the user needs Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management and the operator should preserve the upstream workflow, copied support files, and…

diegosouzapw/awesome-omni-skills · 75 tokens

agent-orchestrator

Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.

marysatasselshaped667/skills-collection-1 · 41 tokens