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/MohmmedAshraf/symbioteWrote 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/mohmmedashraf/symbiote/plugin)<a href="https://agentmods.dev/plugins/mohmmedashraf/symbiote/plugin"><img src="https://agentmods.dev/badge/plugins/mohmmedashraf/symbiote/plugin/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/mohmmedashraf/symbiote/plugin"><img src="https://agentmods.dev/badge/plugins/mohmmedashraf/symbiote/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
symbiote 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 1mo 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": "symbiote",
"version": "0.2.3",
"description": "AI coding companion with persistent memory — code knowledge graph, developer DNA, and architectural intelligence via MCP",
"author": {
"name": "Mohamed Ashraf",
"email": "[email protected]",
"url": "https://outhebox.dev"
},
"repository": "https://github.com/MohmmedAshraf/synapse",
"license": "MIT",
"keywords": [
"mcp",
"code-intelligence",
"knowledge-graph",
"developer-dna",
"architecture",
"memory"
]
}
What it installs
The manifest is a name and a version. 3 agents, 9 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 71 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Agent refactoring-advisor A 20 tokens
- Agent architecture-guardian A 23 tokens
- Agent code-reviewer A 28 tokens
- Hook PostToolUse A not measured
- Hook PostToolUseFailure A not measured
- Hook PreCompact A not measured
- Hook PreToolUse A not measured
- Hook SessionEnd A not measured
- Hook Stop A not measured
- Hook SubagentStart A not measured
- Hook UserPromptSubmit A not measured
- Hook SessionStart A not measured
- MCP server symbiote A not measured
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.
- 1mo ago First seen · 21 lines scan A ce2a1b00d41c
symbiote is a plugin published in the GitHub repository MohmmedAshraf/symbiote (6 stars, last pushed 6mo 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 2026-08-31.
Other plugins, from other repositories
openrig-core
OpenRig canonical skills and hooks for cross-runtime agent topology coordination, continuity, and operating discipline.
memorix
Shared workspace memory for Claude Code and other AI coding agents.
roam-code
Local codebase intelligence + change-safety gates for coding agents. REQUIRES Python 3.10+ and pip install roam-code first — this plugin launches the roam binary from your PATH, and its MCP server cannot start without it. Pre-indexes your repo's symbols, call graph, deps, and git history into SQLite (28 languages.
ijfw
IJFW -- AI efficiency layer for Gemini CLI. 19 workflow skills, 11-event hooks, persistent project memory via MCP. Native policy engine + checkpointing integration. One install layer across 15 AI coding platforms.
ijfw
AI efficiency framework. Smarter output, intelligent routing, persistent memory, context discipline, project workflows. One install. Zero config. It just fucking works.
rekal
Memory for your coding agent. Rekal saves every AI session transcript raw and append-only — no summaries to rot — then recalls the reasoning behind any change: why an approach was chosen, what was tried, what was rejected. Agent agnostic: Claude Code, Cursor, Codex, Gemini, Copilot, Kiro and OpenCode sessions all land.