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 backchainai/backchain-pluginsnpx agentmods add plugins/backchainai/backchain-plugins/marketplacegit clone --depth 1 https://github.com/backchainai/backchain-pluginsGrade A, and why
backchain-plugins 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 yesterday.
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": "backchain-plugins",
"owner": {
"name": "Backchain",
"url": "https://backchain.ai"
},
"metadata": {
"description": "Claude Code plugins by Backchain AI — decision analysis, advisory frameworks, and AI-powered workflows",
"version": "1.0.0",
"license": "Apache-2.0"
},
"plugins": [
{
"name": "advisors",
"source": "./advisors",
"description": "Team of Rivals advisory panel — four specialized advisors for multi-role decision analysis"
},
{
"name": "engram",
"source": "./engram",
"description": "Filesystem-backed agent memory for Claude Code"
},
{
"name": "diogenes",
"source": "./diogenes",
"description": "Senior-reviewer audit for AI-slop and LLM-generation tells in written content"
},
{
"name": "brief",
"source": "./brief",
"description": "Interactive HTML briefs for plans, specs, and decisions — inline controls plus a copy-to-prompt button, in place of a markdown wall"
},
{
"name": "scriptorium",
"source": "./scriptorium",
"description": "Diataxis-grounded documentation authoring and placement: routes a document to tutorial, how-to guide, reference, or explanation, then checks its markdown against CommonMark 0.31.2"
}
]
}
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.
- yesterday First seen · 40 lines scan A 58f3dc4d1634
backchain-plugins is a plugin published in the GitHub repository backchainai/backchain-plugins (4 stars, last pushed 27d 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 2026-08-31.
Other plugins, from other repositories
memory-kit
Memory for coding agents that survives the session boundary — and the builder's layers distilled from a year of daily production use.
memory-kit
Persistent memory for coding agents: a hot cache injected every session and held under three size caps, per-session handoffs, and agent-audited promotion into knowledge articles and rules. Carries the builder's layers too — executor/recon/idea-validator agents, session review, second opinion, agent QA and a system…
skillcheck-free
Validates Claude Code SKILL.md files against 25 contract rules including structure, triggers, anti-patterns, and naming. Works with Claude Code, Claude Desktop/Web, and Cursor.
techwolf-ai-first
Plugin marketplace listing 8 plugins: content-studio, ai-firstify, people-management, techwolf-brand-kit, knowledge-base.
ai-adoption
AI Adoption, three skills for working with your Claude history. token-doctor diagnoses where your Claude Code + Cowork spend goes (length distribution, marathon share, cache rebuilds, per-project health), writes a doctor-style terminal report, and optionally fans out parallel Haiku subagents over your top sessions for.
people-management
AI-augmented management tooling for people managers. Surfaces the right context at the right time: before meetings, during 1:1 prep, when triaging messages, or reviewing customer status. Adapts to your org's performance and management frameworks. Augments managers, never automates.