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 agentmods add skills/hf745316389/ho-codeflow/ho-implnpx skills add hf745316389/ho-codeflow --skill ho-implgit 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-impl)<a href="https://agentmods.dev/skills/hf745316389/ho-codeflow/ho-impl"><img src="https://agentmods.dev/badge/skills/hf745316389/ho-codeflow/ho-impl.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 | $0.00052 | $0.01827 |
| Opus 5 | $0.00026 | $0.00914 |
| Sonnet 5 | $0.00010 | $0.00365 |
| Haiku 4.5 | $0.00005 | $0.00183 |
Grade A, and why
ho-impl 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 5d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement
Build what the design says. You are not redesigning it, and you are not deciding anything it left open.
Before you touch a file
Read change.yaml, the whole of 01-design.md, and any earlier
02-implementation.md from a previous round. Then read every file the design
puts in scope. status must be ready_for_implementation or rework; if
Open questions still lists anything, the design is not ready — say so and
stop.
Set status: implementing.
When the design does not match the project
The design was written against the project at some earlier moment. Acceptance criteria name fixture rows, flags, files, and functions that may not be there.
A design that does not fit what is actually in the project is a question, not a puzzle to solve. Stop, quote the criterion, quote what you found instead, and ask.
This is the failure that shows up most in practice. Five independent agents given one design whose AC named a fixture row that did not exist produced three different repairs and none of them asked.
| Rationalization | Why it fails |
|---|---|
| "There is a clean local fix, so it isn't really a conflict" | The cleanness of your repair says nothing about whether it is the repair the author wanted. |
| "I documented it in a comment next to the code" | A comment in a file is not a report to the person who has to accept the change. |
| "Editing that existing assertion is outside the design's tasks, so I worked around it" | Both the edit and the workaround are decisions the design did not authorize. Noticing that is the moment to stop, not the moment to pick the other one. |
| "It only changes a test fixture, not behaviour" | An assertion is a claim about what the system should do. Changing one changes that claim. |
| "The intent is obvious even though the letter is wrong" | Then say what you think the intent is and get one word back. |
Red flags: "I'll just add a parallel fixture" · "this reflects the larger fixture, not a behaviour change" · "the design clearly meant" · "I'll note it in the deviations section and carry on".
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.
- 5d ago First seen · 169 lines · 52 tokens per session scan A 5aa46c149ab1
ho-impl is a skill published in the GitHub repository hf745316389/ho-codeflow (4 stars, last pushed 22d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,827 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…
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.
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.
stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows.
project-orchestration
Orchestrate multi-agent workflows for feature development using planning agents, context handoff, and stage management.