Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tradecatlabs/fatecatnpx agentmods add skills/tradecatlabs/fatecat/horosa-agentWrote 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/tradecatlabs/fatecat/horosa-agent)<a href="https://agentmods.dev/skills/tradecatlabs/fatecat/horosa-agent"><img src="https://agentmods.dev/badge/skills/tradecatlabs/fatecat/horosa-agent/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/tradecatlabs/fatecat/horosa-agent"><img src="https://agentmods.dev/badge/skills/tradecatlabs/fatecat/horosa-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 200 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 222 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00000 | $0.05839 |
| Opus 5 | $0.00000 | $0.02919 |
| Sonnet 5 | $0.00000 | $0.01168 |
| Haiku 4.5 | $0.00000 | $0.00584 |
Grade A, and why
horosa-agent 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 11d 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 — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Horosa Skill Agent Guide
Use this skill when an AI agent is connected to Horosa Skill through MCP, CLI, Cursor, Claude, Codex, OpenClaw, Open WebUI, or another local-first client and needs to call Horosa metaphysics tools, generate reports, store memory, or debug user-facing results.
Core Rule
Horosa Skill is local-first. After horosa-skill install, algorithms should run through the local runtime, local headless JS engines, and local storage. Do not tell users that a missing field requires MongoDB, port 7897, Xingque Desktop, a remote database, or an external service unless a current doctor / openclaw-check result explicitly says so. If output is missing, describe it as a local tool/result/input issue and suggest a concrete recheck.
If the client exposes native Horosa MCP tools, call those tools directly. In OpenClaw traces this means the agent should see Horosa tools such as horosa_cn_qimen, horosa_cn_liureng_gods, horosa_astro_chart, horosa_agent_guidance, horosa_memory_show, and horosa_report_render. If the trace shows clientToolCount: 0 or no horosa_* tools are available, the MCP server was not attached to that agent session. Stop and tell the user/admin to run:
uv run horosa-skill client openclaw-setup --workspace <the-agent-workspace>
uv run horosa-skill client openclaw-check --workspace <the-agent-workspace> --full
Do not silently fall back to hand-written Python, shell calculations, web snippets, or unscoped CLI calls. CLI fallback is only acceptable as a diagnostic, and it must use the exact HOME, HOROSA_RUNTIME_ROOT, and HOROSA_SKILL_DATA_DIR env block from the generated mcporter config.
Do not hand-calculate Horosa techniques with Exec, shell, Python, JavaScript snippets, web search, or memory-only formulas. If the user asks for a pan/result, call the Horosa MCP or CLI tool and treat the returned export_snapshot as the source of truth. Manual scripts bypass Xingque-compatible defaults, true-solar-time handling, runtime parity fixes, memory, and reports.
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.
- 11d ago First seen · 389 lines · 0 tokens per session scan A 69b8c6a1b85b
horosa-agent is a skill published in the GitHub repository tradecatlabs/fatecat (203 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,839 tokens. 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 2026-08-30.
Other skills, from other repositories
geo-optimizer-skill
Run geo audit first. It scores the site 0–100 across 8 categories and generates a prioritized action list.
yueyuan
A specialised BaZi analysis system, where BaZi is a Chinese birth-chart method based on birth date and time. It is designed for structured analysis with explicit uncertainty and requires the user to check the chart before deeper interpretation.
technocore-chat
Coordinate with other AI agents over plain HTTP GETs — shared rooms, durable notes, long-polling. No POST, no sockets, no client libraries, no account; a fetch tool is enough, and an MCP server fronts the same surface. Use when you need to leave a message for another agent, wait for one, or persist state across your…
liki-bazi
A Chinese traditional fortune-reading tool using BaZi, a birth-chart system based on birth details, and Zi Wei Dou Shu, another Chinese astrology system. It can examine life areas and yearly trends, but its conclusions are for cultural reference, not professional advice.
liki-divination
A traditional Chinese divination skill covering Liuyao readings, Qimen decisions, and selecting auspicious dates. It interprets an automatically generated chart using defined rules and presents the result as cultural guidance, not professional advice.
liki-naming
A Chinese naming tool that combines BaZi, a birth-chart system based on birth details, with traditional name analysis called Sancai-Wuge. It can also assess existing names and help create Chinese names from English names.