A macOS menu-bar app and local interface for reading Mac health data and coding-agent session history. Coding-agent history can include costs, token use, errors, plan limits, and transcripts, while the local server stays on the Mac.

It is for viewing CPU, GPU, memory, network, and temperature data; checking listening ports; and reviewing Claude Code, Codex, pi, and Claude Desktop activity.

It helps answer what the computer and agents are doing without sending the data to a remote server. It also makes earlier sessions easier to inspect.

actvt — Skill for Claude Code by oye-collective/actvt-claude-plugin

Install

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.

Any agent

npx skills add oye-collective/actvt-claude-plugin --skill actvt

Clone the repo

git clone --depth 1 https://github.com/oye-collective/actvt-claude-plugin

Made for: Claude Code.

Or install actvt, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/oye-collective/actvt-claude-plugin/actvt/github.svg)](https://agentmods.dev/skills/oye-collective/actvt-claude-plugin/actvt)

Your own site

<a href="https://agentmods.dev/skills/oye-collective/actvt-claude-plugin/actvt"><img src="https://agentmods.dev/badge/skills/oye-collective/actvt-claude-plugin/actvt/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/oye-collective/actvt-claude-plugin/actvt"><img src="https://agentmods.dev/badge/skills/oye-collective/actvt-claude-plugin/actvt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 956 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00095	$0.00956
Opus 5.5	$0.00038	$0.00382
Sonnet 5.5	$0.00019	$0.00191
Haiku 4.5	$0.00010	$0.00096

Measured 8d ago against content hash 0b16ddd05a0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

actvt scanned grade A with 1 finding 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (actvt.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

those tools with curl. Everything stays on the Mac: the server listens on 127.0.0.1 only.

pi/skills/actvt/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Actvt

Actvt is a macOS menu-bar app that watches the Mac and the AI coding agents on it, and serves its data as tools on a local MCP server. pi has no MCP client, so actvt.sh (next to this file) calls those tools with curl. Everything stays on the Mac: the server listens on 127.0.0.1 only.

Calling a tool

./actvt.sh list                                  # every tool, its arguments, what it returns
./actvt.sh agent_recent_activity '{"days":7}'    # one call; arguments are one JSON object
./actvt.sh system_metrics_snapshot               # tools without arguments need none

Run it from this skill's directory, or by its full path. It prints the tool's result (usually JSON) and exits non-zero when the call fails, with the reason on the first line. Run list once when you are unsure of a tool's arguments: the descriptions there are the reference.

Which tool

The user asks	Tool
What is the machine doing right now?	`system_metrics_snapshot`, or `system_cpu_current`, `system_gpu_current`, `system_memory_current`, `system_network_current`, `system_thermal_current`
How has load changed over the last hour or week?	`system_metrics_history` (`trailingMinutes`), `system_cpu_history`, `system_gpu_history`
What is listening on port N?	`ports_list`
What did my agents cost?	`agent_recent_activity` (per day), `agent_metrics_aggregate`, `agent_project_buckets` (per project)
How much of my plan is left?	`agent_usage_limits`
Find the session where...	`agent_search` (`text`), then `agent_session_summary` with its `compositeKey`
Pick up where a session left off	`agent_resume_session` (`compositeKey`, `tailTurns`)
Which sessions match a filter?	`agent_sessions_query`, with `agent_facet_options` for the models, branches and tools to filter on
What keeps failing?	`agent_error_patterns`, `agent_recent_error_count`
Was it the agent or the machine that stalled?	`session_machine_context` (`compositeKey`)
Sessions on my other machines	`agent_remote_sessions`

Read the full file on GitHub · 63 lines

Files

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.

actvt.sh 3.8 KB runs code

Changes

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.

8d ago First seen · 63 lines · 95 tokens per session scan A 0b16ddd05a0f

Subscribe to this mod's changes

actvt is a skill published in the GitHub repository oye-collective/actvt-claude-plugin (0 stars, last pushed 9d ago), licensed MIT. It adds 95 tokens to every session and 956 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-31.

Analytics and metrics Productivity claude-code-plugins developer-tools macos mcp model-context-protocol

actvt next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
actvtoye-collective/actvt-claude-plugin	Skill	0	9d ago	MIT	A	95	Claude Code
mailbridgepooyanmajd/pmtechdev-mcp-plugins	Skill	0	4d ago	MIT	A	64	Claude Code, Codex
gmail-multiarkaigrowth/gmail-mcp-server	Skill	0	3mo ago	MIT	A	44	Claude Code, Codex
apple-notes-searchconnerkward/mcp-apple-notes	Skill	8	4mo ago	MIT	C	209	Claude Code
gmailvellum-ai/vellum-assistant	Skill	1.5k	today	MIT	A	20	Claude Code, Codex
gmail-triggervellum-ai/vellum-assistant	Skill	1.5k	today	MIT	A	37	Claude Code, Codex
daily-briefingvellum-ai/vellum-assistant	Skill	1.5k	today	MIT	A	75	Claude Code, Codex

actvt