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 arcee-ai/nac --skill nac-onboardinggit clone --depth 1 https://github.com/arcee-ai/nacWrote 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/arcee-ai/nac/nac-onboarding)<a href="https://agentmods.dev/skills/arcee-ai/nac/nac-onboarding"><img src="https://agentmods.dev/badge/skills/arcee-ai/nac/nac-onboarding/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/arcee-ai/nac/nac-onboarding"><img src="https://agentmods.dev/badge/skills/arcee-ai/nac/nac-onboarding.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 | $0.00071 | $0.00618 |
| Opus 5 | $0.00036 | $0.00309 |
| Sonnet 5 | $0.00014 | $0.00124 |
| Haiku 4.5 | $0.00007 | $0.00062 |
Grade C, and why
nac-onboarding scanned grade C with 2 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 9d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/arcee-ai/nac/main/scripts/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/arcee-ai/nac/main/scripts/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NAC onboarding
Get the user to a running nac dashboard as fast as possible, then connect their MCP client. Authentication, model choice, and MCP server setup all happen in the dashboard UI — do not walk the user through them in chat.
Keep credentials private: if the user ever needs to enter a key or complete a device login, they do it themselves in the UI or their own shell; never request a token in chat or write one into a tracked file.
1. Install and launch
-
Check whether
nac-webis available withnac-web --version. -
If it is missing, install the latest stable release:
curl -fsSL https://raw.githubusercontent.com/arcee-ai/nac/main/scripts/install.sh | sh -
Start nac from the repository the user wants it to work on:
nac-webUse
nac-web -C /path/to/project -ywhen a non-interactive launch is useful. Keep the process running. -
Hand the user the dashboard URL (
http://127.0.0.1:3210by default) and confirm it responds. Everything from here — signing in with Arcee or ChatGPT, picking a model, adding MCP servers from the MCP Library — is done in the UI. Point the user at the dashboard's auth and model picker and let them drive.
2. Connect this MCP client to nac
The MCP client is the harness running this session — the agent the user prompted to install the skill. Do not ask which client to use; configure the one you are running in. Add this streamable-HTTP server to your own harness's MCP configuration:
URL: http://127.0.0.1:3210/mcp
Transport: streamable HTTP
This exposes nac session-management tools to the client agent. The listener is intended for the same machine and has no built-in authentication; do not expose it through a tunnel or reverse proxy unless the user adds strong access control.
Use the client's normal MCP configuration mechanism and adapt its configuration syntax around the URL above. Restart or reload the client if it does not pick up the server automatically, then confirm the client can see nac's tools.
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.
- 9d ago First seen · 51 lines · 71 tokens per session scan C 8b999607790a
nac-onboarding is a skill published in the GitHub repository arcee-ai/nac (232 stars, last pushed today), licensed Apache-2.0. It adds 71 tokens to every session and 618 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
autoprompt
Explicit-only useful-first orchestration. Invoke only when the user names autoprompt - typed as /autoprompt or in plain language such as "act in autoprompt mode" - to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Do not infer invocation from…
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
ap-execharness-resolver
L3 executor - EXECHARNESS RESOLVE. Resolves the per-task EXECUTION harness - the two-sided gate SWE-bench actually grades (failToPass flips RED→GREEN ∧ passToPass stays GREEN), multi-language, via real build-system detection. Ingests shipped FAILTOPASS/PASSTOPASS, else derives failToPass from the mission's behavioral…
ap-feature-coordinator
L1 feature coordinator - drives approved ROADMAP.md lanes through their required build/review/verification gates and owns the run-wide feature frontier.