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 nrl-ai/chubnpx agentmods add plugins/nrl-ai/chub/claude-plugingit clone --depth 1 https://github.com/nrl-ai/chubGrade A, and why
chub 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": "chub",
"description": "Context Hub (chub) integration — MCP-powered documentation lookup, team annotations, and project context for AI coding agents",
"version": "0.1.13",
"author": {
"name": "NRL AI",
"url": "https://github.com/nrl-ai/chub"
},
"homepage": "https://github.com/nrl-ai/chub",
"repository": {
"type": "git",
"url": "https://github.com/nrl-ai/chub.git"
},
"license": "MIT",
"keywords": ["documentation", "api", "mcp", "context", "team", "annotations"]
}
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 · 17 lines scan A 8f13bb88e3a5
chub is a plugin published in the GitHub repository nrl-ai/chub (11 stars, last pushed 5mo 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 2026-08-30.
Other plugins, from other repositories
autoharness
Per-symbol maintenance optimizer for an agent's skill layer — learns skills from real runs and keeps them by adherence in use, not by an offline eval score.
faf
Persistent Project Context for AI — IANA-registered .faf format. Run /faf to score your project in Claude Code; install the CLI via bunx faf or npm install -g faf-cli for the full toolkit.
neatcontext marketplace
Save Claude Code work as reusable, domain-aware context.
neatcontext
Save Claude Code work as reusable, domain-aware context.
dev-loop
loop-orchestrator's verification loop (TDD / PDCA / Reflexion) with the plan step FIXED to a wiki-grounded planning methodology (wiki-plan): every design decision is routed to a bundled semantic-layer wiki before code is written. Adds a knowledge-capture loop — sessions emit verified insights, and knowledge-flush…
affirm
Approval gate for project instructions. Surfaces new or modified CLAUDE.md, .claude/rules/ files, and the files they @import at session start; the user explicitly affirms them before Claude treats them as trusted.