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/jovesun-lab/arcgramWrote 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/jovesun-lab/arcgram/arcgram)<a href="https://agentmods.dev/plugins/jovesun-lab/arcgram/arcgram"><img src="https://agentmods.dev/badge/plugins/jovesun-lab/arcgram/arcgram/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/jovesun-lab/arcgram/arcgram"><img src="https://agentmods.dev/badge/plugins/jovesun-lab/arcgram/arcgram.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
arcgram 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 today.
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": "arcgram",
"version": "2.1.2",
"description": "Make AI agent reasoning visible and auditable as an interactive graph. Arcgram turns walls of prose into typed nodes and explicit edges you inspect and correct node by node. Use it as a visual agent harness: propose → draw → self-audit → fix, human in the loop. Outputs one standalone HTML file: no build step, no npm, no CDN, no runtime. Ships authoring plus Checkpoint (diagram structure), Reconcile (diagram vs code), and Validate self-checks. Framework-agnostic and agent-neutral.",
"author": {
"name": "jovesun-lab",
"url": "https://github.com/jovesun-lab"
},
"homepage": "https://arcgram.io",
"repository": "https://github.com/jovesun-lab/arcgram",
"license": "Apache-2.0",
"keywords": [
"diagram",
"node-graph",
"topology",
"dependency-graph",
"workflow",
"visualization",
"agent-skill",
"standalone-html"
],
"skills": [
"./",
"./skills/checkpoint",
"./skills/reconcile",
"./skills/validate"
]
}
What it installs
The manifest is a name and a version. 4 skills travel with it, and installing the plugin installs all of them — 468 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json 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.
- today Changed 76114c0f5b06
- 2d ago Changed 392afc16d2d9
- 29d ago Changed 30113e926df1
- 1mo ago First seen · 29 lines scan A 3265890206e8
arcgram is a plugin published in the GitHub repository jovesun-lab/arcgram (13 stars, last pushed yesterday), 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 2026-08-31.
Other plugins, from other repositories
codyhxyz marketplace
Plugin marketplace listing 12 plugins: prompt-optimizer, create-claude-plugin, create-chrome-extension, first-principles-review, eureka.
alibabacloud-opc
Alibaba Cloud OPC (one-person company) package selection and provisioning for solo developers, with an itemized monthly cost confirmation before any charge.
dokumenty
Operacje na dokumentach: konwersja PDF/Office do Markdown (markitdown, opendataloader-pdf), redlining .docx z Track Changes (redline-docx-pl), anonimizacja i pseudonimizacja PII (let-it-be), terminy procesowe (terminy-procesowe-pl), klauzule umowne (klauzule-kontraktowe-pl), kalkulatory procesowe…
dev-mcp
Narzedzia deweloperskie MateMatic (advanced): spec-driven development, kanon budowy MCP serverow, recenzent PR dla LegalTech AI, generator instalatora marketplace. Bez konektorow.
looptimal
Turns an objective into a delivered, VERIFIED OUTCOME: frames a hash-pinned sealed acceptance suite, designs the right loop (the loop-design wizard, formerly LoopPrint), war-games it forward, executes with dynamic domain-expert sub-agents (maker != checker), and gates completion on a separate verifier re-running the…
craft
Full-stack developer toolkit with integrated workflow automation - 48 commands, 2 agents, 41 skills with standardized dry-run preview mode (29 with --dry-run support). Code, git, site, docs, testing, architecture, CI, distribution, teaching workflows, planning, release pipeline, and ADHD-friendly features including…