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.
npx agentmods add plugins/fergana-labs/stash/marketplace/plugin marketplace add Fergana-Labs/stashgit clone --depth 1 https://github.com/Fergana-Labs/stashGrade A, and why
stash-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
{
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
"name": "stash-plugins",
"description": "Shared memory for AI coding agents \u2014 Claude Code plugin for Stash workspaces, history streaming, and wiki curation.",
"owner": {
"name": "Fergana Labs",
"email": "[email protected]"
},
"plugins": [
{
"name": "stash",
"source": "./plugins/claude-plugin",
"description": "Connect Claude Code to Stash \u2014 stream activity to history, inject agent memory, collaborate in workspaces.",
"version": "0.1.436",
"category": "productivity",
"homepage": "https://joinstash.ai",
"author": {
"name": "Fergana Labs"
}
}
]
}
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 · 23 lines scan A 81e78201ad8f
stash-plugins is a plugin published in the GitHub repository Fergana-Labs/stash (327 stars, last pushed 3d 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
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.
titen
Evidence-grounded collaborative memory for coding agents.
axme-code
(Alpha) Persistent memory, architectural decisions, and safety guardrails for Claude Code. Your agent starts every session with full project context — stack, decisions, patterns, safety rules, and a handoff from the previous session.
wordcount-habitat
The wordcount team's habitat packaged as a plugin: CLAUDE.md skeleton, HARNESS.md constraint set, the spec-implement orchestrator command, the wordcount-style skill, and the standard CI workflow. Adopt with /wordcount-habitat-init.
cortadel
Plugin marketplace listing 1 plugin: cortadel-memory.
nav-spike
TASK-57 v7 hook-channel spike probes (S1-S6). Every hook gates on cwd inside /tmp/nav-v7-spike AND a per-probe arm file, so the plugin is inert everywhere else.