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.
git clone --depth 1 https://github.com/5dive-ai/5dive-pluginsWrote 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/plugins/5dive-ai/5dive-plugins/mod)<a href="https://agentmods.dev/plugins/5dive-ai/5dive-plugins/mod"><img src="https://agentmods.dev/badge/plugins/5dive-ai/5dive-plugins/mod/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/plugins/5dive-ai/5dive-plugins/mod"><img src="https://agentmods.dev/badge/plugins/5dive-ai/5dive-plugins/mod.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mod 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 28d 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
{
"name": "mod",
"description": "5dive telemetry producer, seat panel, command surface and tool-call policy guard for Claude Code function hooks (early access). Publishes turn and session boundaries and the account's usage reading from inside the harness process to a per-seat JSONL sink, so the heartbeat, the pacing floor and the self-update's pending-restart sweep can read a first-class signal instead of inferring idle/busy from pane samples and the task board. Registers /task and /gate, which dispatch to the 5dive CLI in-process. It also draws one line above the prompt naming the row the seat holds, its gate, its grader and its token burn against its budget, at zero context cost. On the NON-FRESH seats it can additionally compact the conversation at a turn boundary, so the next dispatched goal lands on a summary instead of the whole accumulated window; that half pins any unanswered human gate or standing directive back into the compacted transcript. And it enforces a table-driven deny list over tool calls (policy/guard.json), so a rule that today costs every seat tokens on every turn and is caught after the fact is refused before the tool runs, with the reason handed to the model. Every capability is off unless the seat opts in; the compact hook is the only one that rewrites a call and the guard is the only one that can refuse one.",
"version": "0.6.0",
"author": {
"name": "5dive",
"email": "[email protected]"
},
"homepage": "https://github.com/5dive-ai/5dive-plugins/tree/main/plugins/mod",
"keywords": [
"telemetry",
"function-hooks",
"observability",
"above-prompt",
"claude-code-2.1.278"
]
}
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.
- 28d ago First seen · 18 lines scan A 116bc9e41fb6
mod is a plugin published in the GitHub repository 5dive-ai/5dive-plugins (2 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-21.
Other plugins, from other repositories
graph-it-live
Dependency, call-graph, impact, and architecture analysis for codebases.
antigravity
Antigravity plugin for Claude Code with TRAID Design System: 5 canonical HTML templates (traid-dark, traid-light, stripe-press, notion-docs, magazine) for branded report generation from markdown. Plus audio & video transcription (/agy:transcribe, /agy:media), a local NotebookLM (/agy:notebook — sweep a folder of…
agy
Delegate coding tasks to Google's Antigravity (agy) CLI / Antigravity IDE from Claude Code (Google Agy) — full rescue, resume, background execution, review, status tracking, and stop-time review gate.
gemini-swarm
Make Gemini your default writer and image generator: the orchestrator plans and reviews while parallel agy (Antigravity CLI / Gemini) sessions do the writing, plus a gemini-imagegen skill that generates real images via Gemini's generateimage tool.
slack-workspace
The entire Slack Web API for Claude Code — 201 methods, approval-gated sending, a cached workspace reference, and scheduled-job alerting. Backed by the elnora-slack CLI.
dispatch
Delegate a task to an external AI CLI — OpenAI Codex (/codex) or Google Antigravity (/agy, multi-model: Gemini/Claude/GPT-OSS): second opinions, parallel checks, side tasks, images.