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.
/plugin marketplace add artemavrin/occamnpx agentmods add plugins/artemavrin/occam/marketplacegit clone --depth 1 https://github.com/artemavrin/occamGrade A, and why
occam marketplace 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 2d 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": "occam",
"owner": {
"name": "Artem Mavrin",
"email": "[email protected]"
},
"plugins": [
{
"name": "occam",
"source": "./",
"description": "Execution-shape razor: triages any non-trivial task into the simplest sufficient shape — disciplined loop, parallel fan-out, or milestone graph with shared state — and executes it. Agents should not be multiplied beyond necessity.",
"version": "0.1.0",
"author": {
"name": "Artem Mavrin"
},
"license": "MIT",
"keywords": ["orchestration", "multi-agent", "subagents", "planning", "workflow", "graph", "loop"]
}
]
}
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.
- 2d ago First seen · 21 lines scan A cde24aa744e8
occam marketplace is a plugin published in the GitHub repository artemavrin/occam (1 stars, last pushed 1mo ago), licensed MIT. 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
pilotfish
macOS and Linux Claude Code Plugin beta with hook-based ambient policy activation and namespaced role agents.
longgraph-skill
Long-horizon agent skill: durable loop-graph runs (executor + clean-context supervisor), verified gates, owner A/B/C cards. Works with Claude Code, Codex, Cursor, and Grok Build. Invoke /longgraph, /loop-converge, /loop-deliver, or /loop-research.
team-shinchan
The Agent Harness for Claude Code — Guardrails, Observability, and Quality Gates for AI-Powered Development. 15 specialist agents with structured workflows, budget controls, analytics, and self-learning.
agent-taskgraph
PMO-led native Claude Code Agent Teams with isolated contexts and document handoffs.
relay
Delegate work packets from a lead Claude Code session to executor sessions in their own iTerm tabs, with session reuse instead of always spawning fresh.
claude-mpm
Multi-Agent Project Manager - Orchestrate Claude with specialized agents for research, engineering, QA, ops, and more.