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 chipi/agentic-ai-homelab --skill new-docgit clone --depth 1 https://github.com/chipi/agentic-ai-homelabWrote 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/chipi/agentic-ai-homelab/new-doc)<a href="https://agentmods.dev/skills/chipi/agentic-ai-homelab/new-doc"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/new-doc/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/chipi/agentic-ai-homelab/new-doc"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/new-doc.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00079 | $0.00573 |
| Opus 5 | $0.00039 | $0.00287 |
| Sonnet 5 | $0.00016 | $0.00115 |
| Haiku 4.5 | $0.00008 | $0.00057 |
Grade A, and why
new-doc 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 10d 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
new-doc
Create a new doc in the right place, numbered and wired, so it's discoverable and the strict build stays green. Never leave an orphan page.
Pick the type
| Type | Dir | Filename | For |
|---|---|---|---|
| ADR | docs/adr/ |
ADR-NNNN-slug.md |
architectural decisions that govern the repo's design |
| RFC | docs/rfc/ |
RFC-NNNN-slug.md |
proposals under discussion, before a decision |
| Recipe | docs/recipes/ |
slug.md |
a runbook / how-to for a repeatable operation |
| WIP note | docs/wip/ |
slug.md |
plans, analyses, in-progress work |
ADR vs decision-log: if a future contributor needs it to make a consistent
change → ADR. A one-shot operational choice (port, image, defer-vs-do) → append
a D-NNNN entry to docs/history/0002-decisions.md instead.
Steps
- Next id. For numbered types, find the highest existing
NNNNin the dir and add 1 (never renumber). Slug = short kebab-case. - Scaffold by matching an existing sibling. Required frames:
- ADR:
# ADR-NNNN — <title>·**Status:** Proposed·**Date:**· then ctx (the problem) / Decision / Consequences (positive / negative / neutral) / Alternatives considered. Keep under ~200 lines; split if it grows past that. - Recipe: title · Why this exists · Quick reference · steps · Verification · Troubleshooting.
- ADR:
- Wire the mkdocs nav. Add the page under its section in
mkdocs.ymlnav:(the nav is explicit — an unlisted page underdocs/is an orphan). Preserve sibling ordering. - Update the section index (
README.md) if it enumerates entries. - Validate. Run the
docs-preflightskill — the strict build must stay green.
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.
- 10d ago First seen · 40 lines · 79 tokens per session scan A a16495e0f99f
new-doc is a skill published in the GitHub repository chipi/agentic-ai-homelab (2 stars, last pushed 3d ago), licensed MIT. It adds 79 tokens to every session and 573 once invoked, about $0.0004 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
mikromcp
Use when managing, configuring, or troubleshooting MikroTik RouterOS devices through the MikroMCP server — picking the right tool, running safe (dry-run, confirmed, rollback-able) changes, fleet operations, and diagnosing network issues.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.