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/agentic-in/elephant-agent/inferencenpx skills add agentic-in/elephant-agent --skill inferencegit clone --depth 1 https://github.com/agentic-in/elephant-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/agentic-in/elephant-agent/inference)<a href="https://agentmods.dev/skills/agentic-in/elephant-agent/inference"><img src="https://agentmods.dev/badge/skills/agentic-in/elephant-agent/inference.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 | $0.00021 | $0.00301 |
| Opus 5 | $0.00010 | $0.00151 |
| Sonnet 5 | $0.00004 | $0.00060 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
Inference 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 4d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
21 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.
- llama-cpp/references/advanced-usage.md 11 KB
- llama-cpp/references/optimization.md 1.6 KB
- llama-cpp/references/quantization.md 4.8 KB
- llama-cpp/references/server.md 2.2 KB
- llama-cpp/references/troubleshooting.md 8.7 KB
- llama-cpp/SKILL.md 12 KB
- obliteratus/references/analysis-modules.md 6.1 KB
- obliteratus/references/methods-guide.md 6.6 KB
- obliteratus/SKILL.md 15 KB
- obliteratus/templates/abliteration-config.yaml 1.2 KB
- obliteratus/templates/analysis-study.yaml 1.3 KB
- obliteratus/templates/batch-abliteration.yaml 1.2 KB
- outlines/references/backends.md 14 KB
- outlines/references/examples.md 21 KB
- outlines/references/json_generation.md 15 KB
- outlines/SKILL.md 15 KB
- vllm/references/optimization.md 5.6 KB
- vllm/references/quantization.md 6.6 KB
- vllm/references/server-deployment.md 5.1 KB
- vllm/references/troubleshooting.md 8.8 KB
- vllm/SKILL.md 8.7 KB
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.
- 4d ago First seen · 36 lines · 21 tokens per session scan A b409fcf63db0
Inference is a skill published in the GitHub repository agentic-in/elephant-agent (582 stars, last pushed 7d ago), with no licence file. It adds 21 tokens to every session and 301 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
skill-to-subagent
Turn an existing pi skill into an isolated subagent and wire it into a project's implementation pipeline. Decides fitness first, writes the bridge agent, routes the model, tunes context inheritance, and wires a spawn checkpoint. Use on "wrap this skill as a subagent", "turn X into a subagent", "should this be a…
anti-slop-frontend
A mechanical, countable anti-slop checklist for AI-generated frontend. Catches the specific signatures an undirected model defaults to: AI-purple glows, Inter-everywhere, em-dashes, div-based fake screenshots, eyebrow-on-every-section, beige+brass "premium" palettes, generic Jane Doe / Acme data. Advisory layer that…
doctor
Diagnose why pi-flows, the Anthropic-messages bridge, model resolution, a pi install, a peer, a plugin/bridge, or a build/reload is broken in the pi-agent-dashboard. Derives every fact live (works with the server down). Use on "flow won't show", "bridge waitingpeers", "pi version mismatch", "which pi is this using"…
code_interpreter
在隔离沙盒中执行 Python 代码，用于数据分析、数值计算、格式转换、图表数据生成等需要真正运行代码才能得出结果的任务。.
edit-flow
Create and edit pi-flows flows and agents from the main session. Use when the user wants to create a new flow, add or change an agent, or edit an existing flow/agent. Covers agent frontmatter, flow YAML, step types, model references, the flowagents and flowwrite tools, write locations, and how to fix validation errors.
huggingface-hub
Hugging Face Hub — model discovery, download, inference, and upload.