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 agentmods add skills/oye-collective/actvt-claude-plugin/setupnpx skills add oye-collective/actvt-claude-plugin --skill setupgit clone --depth 1 https://github.com/oye-collective/actvt-claude-pluginWrote 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/oye-collective/actvt-claude-plugin/setup)<a href="https://agentmods.dev/skills/oye-collective/actvt-claude-plugin/setup"><img src="https://agentmods.dev/badge/skills/oye-collective/actvt-claude-plugin/setup.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.00819 |
| Opus 5 | $0.00026 | $0.00409 |
| Sonnet 5 | $0.00010 | $0.00164 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
actvt-setup 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST http://127.0.0.1:4096/mcp \ How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connecting Actvt
Actvt's MCP server runs inside the Actvt macOS app. It is not a standalone process, so it only answers while the app is running with the server switched on. Work through these checks in order and stop at the first one that fails.
1. Is Actvt installed?
ls -d /Applications/Actvt.app
If it is missing, the user needs to install Actvt from https://actvt.io. It is macOS only and requires macOS 15.5 or later. Nothing else here will work until then.
2. Is the server switched on?
The endpoint descriptor only exists while the server is running.
ls -l ~/Library/Application\ Support/ACTVT/mcp/endpoint.json
If the file is missing, tell the user to open Actvt and turn on Settings > MCP > Enable MCP server. This is a GUI toggle, so they have to do it. Once it is on, the file appears within a second or two.
3. Which port did it bind?
plutil -extract url raw -o - ~/Library/Application\ Support/ACTVT/mcp/endpoint.json
Expect http://127.0.0.1:4096/mcp, which is what this plugin points at.
Actvt prefers 4096 but falls back to another port when something else already holds it. If the URL shows a different port, the user should either free 4096 and restart Actvt, or export the real endpoint before starting Claude Code:
export ACTVT_MCP_URL="$(plutil -extract url raw -o - ~/Library/Application\ Support/ACTVT/mcp/endpoint.json)"
4. Does the auth helper work?
"${CLAUDE_PLUGIN_ROOT}/scripts/actvt-auth.sh"
It should print a single JSON object containing an Authorization header. The script prints the
specific reason on failure, so read its output rather than guessing.
5. Does the server answer?
This isolates the server from Claude Code, so a failure here means the problem is Actvt rather than the plugin.
TOKEN=$(plutil -extract token raw -o - ~/Library/Application\ Support/ACTVT/mcp/endpoint.json)
curl -s -X POST http://127.0.0.1:4096/mcp \
-H "Authorization: Bearer $TOKEN" \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
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.
- 4d ago First seen · 84 lines · 52 tokens per session scan A 4c164e037835
actvt-setup is a skill published in the GitHub repository oye-collective/actvt-claude-plugin (0 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 819 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
remarc
Manage Remarc session comments and contextual feedback. Use when the user mentions Remarc sessions, comments, handoff, triage, review, addressing, resolving, status updates, or summaries.
sync-html-design-system
Use when the user changes a UI element in Remarc's macOS app (icon, badge, type label, component variant) and asks to reflect, mirror, encode, or sync it in the HTML design system — typically phrased as "add this to the design system", "mirror in HTML", "encode this on the web version", or "make sure the design system…
merge
Merge a worktree feature branch into main with build verification and cleanup.
apple-photos
Use this skill when the user wants to query, view, organize, or export photos from their macOS Apple Photos library — searching by date/import-date/album/keyword/person/label/place/GPS-radius/media-type/aesthetic-score/OCR-text, viewing photos inline as thumbnails, acting on the live Photos.app selection, finding…
vocab
Add or remove words from the speech recognition vocabulary hints. Use when the user wants to add a word to the dictionary or fix a speech recognition misrecognition.
swift-fast-mcp
Generate a complete MCP server project in Swift using the FastMCP library. Use when asked to create a Swift MCP server, build an MCP tool server, or scaffold a Model Context Protocol project in Swift.