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 hf745316389/ho-codeflow --skill ho-designgit clone --depth 1 https://github.com/hf745316389/ho-codeflowWrote 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/hf745316389/ho-codeflow/ho-design)<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.
<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>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 | $0.00051 | $0.01534 |
| Opus 5 | $0.00026 | $0.00767 |
| Sonnet 5 | $0.00010 | $0.00307 |
| Haiku 4.5 | $0.00005 | $0.00153 |
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.
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".
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.
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 · 140 lines · 51 tokens per session scan A ffa8d3caa340
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.
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…
Subagent Driven Development
Orchestrate specialized, autonomous AI agents to execute parallel subtasks with strict boundaries.
Cursor Workflow Optimizer
Master Cursor IDE with optimal configurations, custom rules, MCP integrations, and workflow patterns that 10x developer productivity.
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.
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…
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.