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 scoped-agentsgit 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/scoped-agents)<a href="https://agentmods.dev/skills/chipi/agentic-ai-homelab/scoped-agents"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/scoped-agents/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/scoped-agents"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/scoped-agents.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 | $0.00086 | $0.00811 |
| Opus 5.5 | $0.00034 | $0.00324 |
| Sonnet 5.5 | $0.00017 | $0.00162 |
| Haiku 4.5 | $0.00009 | $0.00081 |
Grade A, and why
scoped-agents 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 2mo 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scoped-agents
Create a folder-scoped AGENTS.md and register it in the repo-root AGENTS.md,
following the layering rules below. Use it to add new scoped rules, or to split
an overgrown root AGENTS.md into per-folder files.
Load-bearing rules (do not violate)
AGENTS.mdis the source of truth — harness-agnostic, carries the real rules.CLAUDE.mdis a THIN layer that@AGENTS.md-imports and adds only Claude-specific notes. Never invert this. If a repo has a fatCLAUDE.mdand noAGENTS.md, fix that first (move the rules intoAGENTS.md, reduceCLAUDE.mdto the import + Claude-only notes).- Scoped files never duplicate the root or the global rules. A folder
AGENTS.mdholds only what is specific to that folder. Repo-wide rules stay at the root; cross-repo operator rules stay in the global~/.config/AGENTS.md. - More-specific wins. Precedence: direct chat > memory > deeper scoped
(
a/b/AGENTS.md) > shallower scoped (a/AGENTS.md) > root > global.
Steps
- Confirm the pattern. Repo root has
AGENTS.md; if Claude Code is used,CLAUDE.mdis thin and imports it (@AGENTS.md). Establish that before scoping. - Create
<folder>/AGENTS.mdfrom the template below — only rules that truly belong to that folder. If those rules currently live in the root, MOVE them (don't leave a duplicate). - Register it in the root
AGENTS.mdunder## Scoped AGENTS.md(create the section + table if missing). One row: linked path + one-line scope. - If splitting the root: verify every moved rule lands in exactly one scoped file and the root still links to it. The root shrinks; nothing is lost. Grep for stale references to any rule you moved (e.g. "rule #N").
- Validate. If the scoped file sits inside a docs tree built by mkdocs/etc.,
make sure it doesn't publish as an orphan page (exclude it) — then run the
docs-preflightskill.
Template — <folder>/AGENTS.md
# AGENTS.md — <folder>/ (scoped rules)
Loaded when working under `<folder>/`. Layers on top of the repo-root
[`AGENTS.md`](<relative-path-to-root>AGENTS.md); never duplicates or contradicts it.
<one sentence: what this folder is and what the rules here govern>
## <Rule heading>
<the folder-specific rule; include the WHY when it is non-obvious>
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.
- 2mo ago First seen · 68 lines · 86 tokens per session scan A 3447a5f776d5
scoped-agents is a skill published in the GitHub repository chipi/agentic-ai-homelab (3 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 811 once invoked, about $0.0003 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 2026-08-31.
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.
worker-integration
Worker-Agent integration for intelligent task dispatch and performance tracking.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
evo2-nim
Generate and analyze DNA sequences using NVIDIA's Evo 2 BioNeMo NIM microservice. Use for Evo2/Evo 2, DNA generation, genomic sequence generation, hosted generation, local Docker deployment, local forward passes, layer outputs, logits, sampled probabilities, and BioNeMo NIM workflows.