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 xiaotianfotos/homerail --skill homerail-dag-opsgit clone --depth 1 https://github.com/xiaotianfotos/homerailWrote 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/xiaotianfotos/homerail/homerail-dag-ops)<a href="https://agentmods.dev/skills/xiaotianfotos/homerail/homerail-dag-ops"><img src="https://agentmods.dev/badge/skills/xiaotianfotos/homerail/homerail-dag-ops/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/xiaotianfotos/homerail/homerail-dag-ops"><img src="https://agentmods.dev/badge/skills/xiaotianfotos/homerail/homerail-dag-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00153 | $0.04248 |
| Opus 5 | $0.00077 | $0.02124 |
| Sonnet 5 | $0.00031 | $0.00850 |
| Haiku 4.5 | $0.00015 | $0.00425 |
Grade A, and why
homerail-dag-ops scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "$HOMERAIL_MANAGER_URL/api/dag-status/<run_id>/node/<node_id>/result" How it starts
The opening of the file, as written. The whole thing — 441 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HomeRail DAG Operations (TypeScript Backend)
Before acting, apply homerail-shared rules. This skill assumes the local runtime
is already ready. If not, run hr start or use homerail-install-ops.
When this Skill is loaded inside the HomeRail Manager Agent, use the harness's
native shell and the HomeRail CLI whenever they provide the clearest or most
complete path. Prefer --json so command results remain structured. Dedicated
Manager Tools such as list_orchestrations, create_and_run, invoke_run, and
get_run_status are equivalent shorter paths for operations they already
cover; they are not the only valid execution route. For abstract pattern selection, load
homerail-dag-patterns and use either its Manager Tools or the corresponding
hr patterns commands before running the instantiated workflow.
Supervised multi-Actor live panels
Use the concrete assets/orchestrations/multi-actor-live-report.yaml.template
Workflow only when the user wants three stable, independently grounded panels
for evidence research, skeptical analysis, and a screenshot-ready publication
draft. It explicitly declares digest-pinned Surface views,
report_surface_state, a three-Actor join, and await_command, so all three
Actors remain addressable after their first round.
Choose exactly three Actors when each panel remains useful by itself, each has a non-overlapping responsibility, and the user benefits from later per-panel follow-ups. Share one source identity and evidence boundary. Parallelize only independent work. When analysis or publication must consume research output, author explicit data edges or structured handoffs instead of using the bundled parallel template unchanged. Use one Manager-owned Block for a simple answer or single report, and never add Actors merely to make the task look sophisticated.
Inside the Manager Agent, start it with start_supervised_dag and the exact
yamlPath; pass the user's full objective as prompt and an available runtime
profile only when one is required. Do not substitute the abstract
orchestrator-workers pattern: that pattern performs dynamic fan-out and
verification but intentionally has no live Surface or follow-up contract.
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.
- 13d ago First seen · 441 lines · 153 tokens per session scan A f9ce6c176a34
homerail-dag-ops is a skill published in the GitHub repository xiaotianfotos/homerail (951 stars, last pushed today), licensed MIT. It adds 153 tokens to every session and 4,248 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…