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.
git clone --depth 1 https://github.com/CHANGGELY/claude_codex_gemini_memWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/changgely/claude_codex_gemini_mem/gemini-extension)<a href="https://agentmods.dev/plugins/changgely/claude_codex_gemini_mem/gemini-extension"><img src="https://agentmods.dev/badge/plugins/changgely/claude_codex_gemini_mem/gemini-extension/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/changgely/claude_codex_gemini_mem/gemini-extension"><img src="https://agentmods.dev/badge/plugins/changgely/claude_codex_gemini_mem/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
gemini-mem-extension 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 11d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
32 files beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/logo.svg 2.3 KB
- scripts/analyze-transformations-smart.js 14 KB runs code
- scripts/bug-report/cli.ts 7.2 KB runs code
- scripts/bug-report/collector.ts 9.6 KB runs code
- scripts/bug-report/index.ts 5.5 KB runs code
- scripts/build-hooks.js 8.9 KB runs code
- scripts/build-viewer.js 2.4 KB runs code
- scripts/build-worker-binary.js 799 B runs code
- scripts/debug-transcript-structure.ts 3.8 KB runs code
- scripts/discord-release-notify.js 3.6 KB runs code
- scripts/dump-transcript-readable.ts 3.4 KB runs code
- scripts/endless-mode-token-calculator.js 18 KB runs code
- scripts/export-memories.ts 6.0 KB runs code
- scripts/extract-prompts-to-yaml.cjs 7.0 KB runs code
- scripts/extract-rich-context-examples.ts 7.2 KB runs code
- scripts/extraction/extract-all-xml.py 4.4 KB runs code
- scripts/extraction/filter-actual-xml.py 5.8 KB runs code
- scripts/extraction/README.md 1.7 KB
- scripts/find-silent-failures.sh 1.2 KB runs code
- scripts/format-transcript-context.ts 7.0 KB runs code
- scripts/generate-changelog.js 2.9 KB runs code
- scripts/import-memories.ts 3.0 KB runs code
- scripts/publish.js 5.2 KB runs code
- scripts/smart-install.js 6.9 KB runs code
- scripts/sync-marketplace.cjs 3.5 KB runs code
- scripts/sync-to-marketplace.sh 1.5 KB runs code
- scripts/test-transcript-parser.ts 5.6 KB runs code
- scripts/transcript-to-markdown.ts 6.9 KB runs code
- scripts/translate-readme/cli.ts 6.1 KB runs code
- scripts/translate-readme/examples.ts 4.0 KB runs code
- scripts/translate-readme/index.ts 12 KB runs code
- scripts/translate-readme/README.md 5.9 KB
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.
- 11d ago First seen · 12 lines scan A c9805682fa70
gemini-mem-extension is a plugin published in the GitHub repository CHANGGELY/claude_codex_gemini_mem (6 stars, last pushed 11d ago), with no licence file. 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 2026-10-05.
Other plugins, from other repositories
iai-memory
Persistent local memory for your assistant: every turn captured verbatim, relevant memory injected at session start and before each turn, and fourteen memory tools over MCP. Requires the iai-pme package (pip install iai-pme).
mengram marketplace
Plugin marketplace listing 1 plugin: mengram.
mengram
Persistent memory for Claude Code that survives /clear, machine switches, and team handoffs. Hosted memory backend with hybrid retrieval, temporal decay, and cross-device sync.
mnemoverse-memory
Persistent memory for AI agents, shared across tools: write a memory in one MCP client, recall it in another. OAuth sign-in, no API key to paste.
perenna
A lightweight, Git-backed permanent memory for AI agents.
captain-memo
Cross-AI local memory layer for Claude Code, Codex, Gemini CLI, Antigravity, goose, Cursor, opencode, Kimi CLI and more: hybrid search, six summarizer providers, hosted or local embedder. Replaces claude-mem.