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-flowgit 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-flow)<a href="https://agentmods.dev/skills/hf745316389/ho-codeflow/ho-flow"><img src="https://agentmods.dev/badge/skills/hf745316389/ho-codeflow/ho-flow.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 | $0.00045 | $0.01459 |
| Opus 5 | $0.00023 | $0.00730 |
| Sonnet 5 | $0.00009 | $0.00292 |
| Haiku 4.5 | $0.00005 | $0.00146 |
Grade A, and why
ho-flow 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 7d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flow
Set up the change, then run the phases in order. The phase skills do the work; this one decides which phase runs, and where the flow stops.
Reading the request
solo <request> one agent runs every phase
solo auto <request> the same, without pausing after the design
relay <request> each phase hands off to another agent
If the request names no mode, use mode from .ho/config.yaml. If there is no
config, use solo and say so.
auto is an option on one task, never a mode and never a stored setting. It
does not survive into the next request.
Setting up
If .ho/ does not exist, create it: copy the protocol and config templates in,
then tell the user what you added. Do not silently add a directory to someone's
project.
If one or more changes are already open and the request does not name one, list them and ask. Do not infer from recency, from ordering, or from which looks more prepared, and do not run all of them.
Otherwise create .ho/changes/YYYY-MM-DD-<slug>/change.yaml with
status: draft.
Names
These are the names. Do not invent variants — the next agent looks for exactly these:
.ho/config.yaml
.ho/protocol.md
.ho/changes/YYYY-MM-DD-<slug>/change.yaml
.ho/changes/YYYY-MM-DD-<slug>/01-design.md
.ho/changes/YYYY-MM-DD-<slug>/02-implementation.md
.ho/changes/YYYY-MM-DD-<slug>/03-review.md
status is one of draft, ready_for_implementation, implementing,
ready_for_review, rework, complete, abandoned. Nothing else — a status
you coined is a status no other agent and no validator understands. There is no
blocked and no reviewed: a change that stopped on a question keeps the
status of the phase it stopped in, and a change whose review passed is
complete.
Configuration
Read .ho/config.yaml: mode when the request names none, paths.root and
paths.changes if the project moved the directory from the default. auto is
never read from there — it is an option on one request.
Setting an approval key to false says the project does not want a routine
prompt for that class of action. It does not authorize anything, and the list
under What auto does not cover stands whatever the config says.
What ships with it
4 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.
- 7d ago First seen · 154 lines · 45 tokens per session scan A 5e29e1743161
ho-flow is a skill published in the GitHub repository hf745316389/ho-codeflow (4 stars, last pushed 25d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,459 once invoked, about $0.0002 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.