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 KeyArgo/custodian-kernel --skill replicate-rungit clone --depth 1 https://github.com/KeyArgo/custodian-kernelWrote 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/keyargo/custodian-kernel/replicate-run)<a href="https://agentmods.dev/skills/keyargo/custodian-kernel/replicate-run"><img src="https://agentmods.dev/badge/skills/keyargo/custodian-kernel/replicate-run/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/keyargo/custodian-kernel/replicate-run"><img src="https://agentmods.dev/badge/skills/keyargo/custodian-kernel/replicate-run.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 | $0.00020 | $0.00119 |
| Opus 5.5 | $0.00008 | $0.00048 |
| Sonnet 5.5 | $0.00004 | $0.00024 |
| Haiku 4.5 | $0.00002 | $0.00012 |
Grade A, and why
replicate-run 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 1mo 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.
What it actually says
Replicate Run
Run any Replicate model (image gen, audio, video) by version ID
What ships with it
1 file 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.
- 1mo ago First seen · 20 lines · 20 tokens per session scan A 87a15653e133
replicate-run is a skill published in the GitHub repository KeyArgo/custodian-kernel (120 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 119 once invoked, about $0.0001 per session on Opus 5.5. 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
enterprise-fde-识别AI节点
A template for a company-specific skill that classifies business-process nodes by how suitable they are for AI automation. It uses the process inputs, rules, owner, time, and pain point as evidence.
cordis-plugin-sofagent-inject
A sofagent plugin that loads company constraints through several prompt-building layers when the agent starts.
constitutional-ai
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
implementing-llm-guardrails-for-security
Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII detection and content…
release-gate-loop
A release check that tests a change, reports whether it passes, and can run a limited fix-and-retest cycle. A release is the act of making a software version available.