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 DeevsDeevs/agent-systemnpx agentmods add plugins/deevsdeevs/agent-system/marketplacegit clone --depth 1 https://github.com/DeevsDeevs/agent-systemGrade A, and why
deevs-agent-system 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "deevs-agent-system",
"owner": {
"name": "Deevs",
"email": "[email protected]"
},
"metadata": {
"description": "Deevs' marketplace for Claude Code, Open Code, and other agentic AI systems",
"version": "0.0.4"
},
"plugins": [
{
"name": "alpha-squad",
"description": "Five hypothesis generators attacking from complementary angles: value, flows, networks, microstructure/entropy, causal mechanisms",
"source": "./alpha-squad",
"agents": [
"./agents/fundamentalist.md",
"./agents/vulture.md",
"./agents/network-architect.md",
"./agents/book-physicist.md",
"./agents/causal-detective.md"
]
},
{
"name": "mft-research-experts",
"description": "Orchestration, data validation, risk geometry, hypothesis execution, and forensic audit for quantitative research",
"source": "./mft-research-experts",
"agents": [
"./agents/mft-strategist.md",
"./agents/data-sentinel.md",
"./agents/factor-geometer.md",
"./agents/skeptic.md",
"./agents/forensic-auditor.md"
]
},
{
"name": "chain-system",
"description": "Multi-session workflow chains for maintaining linked context across conversations",
"source": "./chain-system",
"commands": ["./commands/"]
},
{
"name": "dev-experts",
"description": "Critical developer personas: architect, devops detective, rust/python/cpp purists, grumpy reviewer, testing specialist",
"source": "./dev-experts",
"agents": [
"./agents/architect.md",
"./agents/devops.md",
"./agents/cpp-dev.md",
"./agents/python-dev.md",
"./agents/reviewer.md",
"./agents/rust-dev.md",
"./agents/tester.md"
]
},
{
"name": "bug-hunters",
"description": "Systematic bug hunting with spec reconstruction, adversarial validation, and confidence-ranked reports",
"sWhat 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 · 111 lines scan A 9e59e0aa8347
deevs-agent-system is a plugin published in the GitHub repository DeevsDeevs/agent-system (40 stars, last pushed 1mo ago), 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 2026-08-30.
Other plugins, from other repositories
agent-inject
Inject copilot-api rules and SubagentStart agent context.
borski
Travel hacking plugins by Borski. Flights, hotels, points, miles, awards.
superset
Plugin marketplace listing 1 plugin: superset.
claude
Persistent memory for Claude Code. Capture work across sessions and recall relevant context.
claude-architect
CLI coding-agent orchestration for Claude through Codex, OpenCode, Pi, and Pythinker Code, with a commitment-boundary advisor.
3xa-harness
Discipline skills for agents doing long-running real work: freeze the scope, gate what only a human can judge, log the decisions, close out honestly.