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 NickCirv/engramnpx agentmods add plugins/nickcirv/engram/marketplacegit clone --depth 1 https://github.com/NickCirv/engramGrade A, and why
engram-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.
Copies of this mod
1 near-identical copy found in the catalogue:
- engram-marketplace — 100% identical, 0 lines differ
What it actually says
{
"name": "engram-marketplace",
"owner": {
"name": "Nicholas Ashkar",
"url": "https://github.com/NickCirv"
},
"plugins": [
{
"name": "engram",
"source": "./engram",
"description": "Local-first context spine for Claude Code. 89% measured token reduction. Knowledge graph + bi-temporal mistakes + MCP server.",
"version": "3.4.0",
"category": "context",
"keywords": ["context", "memory", "token-reduction", "mcp", "local-first"],
"author": {
"name": "Nicholas Ashkar",
"url": "https://github.com/NickCirv"
},
"homepage": "https://github.com/NickCirv/engram",
"license": "Apache-2.0"
}
]
}
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 · 24 lines scan A dd6dfcdc33ef
engram-marketplace is a plugin published in the GitHub repository NickCirv/engram (141 stars, last pushed 2mo 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
qualixar
Plugin marketplace listing 2 plugins: superlocalmemory, superlocalmemory-codex.
superlocalmemory-codex
Local-first agent memory with auditable hybrid retrieval — the Codex build, with Codex-shaped rules, hooks and launcher.
superlocalmemory
Local-first agent memory + reversible context compression and KV cache, as an MCP server. 34-tool code profile with graph intelligence.
nexus-memory
Persistent memory for Claude Code via Qdrant. Auto-Recall injects relevant memories before each prompt. Auto-Capture stores facts after each turn. Self-hosted, private, universal.
dhevenddra
Dhevenddra's Claude Code plugins. Hosts forensic-deepdive: a persistent code knowledge graph + 9 composite MCP tools for AI coding agents.
forensic-deepdive-codebase
Forensic codebase brief for surfacev080 — five markdown artifacts (MAP, HOTPATHS, ARCHAEOLOGY, MENTALMODEL, AGENTBRIEF) plus five single-intent Claude skills covering exploring / debugging / impact-analysis / refactoring / onboarding workflows.