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 iliaal/codesagenpx agentmods add plugins/iliaal/codesage/marketplacegit clone --depth 1 https://github.com/iliaal/codesageGrade A, and why
codesage 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.
What it actually says
{
"name": "codesage",
"owner": {
"name": "Ilia Alshanetsky",
"url": "https://github.com/iliaal"
},
"metadata": {
"description": "Claude Code integration for CodeSage: a single global MCP that serves semantic search, structural graph, impact analysis, and context export across every onboarded project, plus slash commands for onboarding, reset, reindex, retrieval benchmarking, and a subagent-driven review workflow over feature slices",
"version": "0.22.0"
},
"plugins": [
{
"name": "codesage-tools",
"description": "CodeSage integration: onboarding (/codesage-onboard / -reset / -reindex), retrieval benchmarks (/codesage-bench / -eval), and a subagent-driven review workflow (/codesage-review / -triage / -revalidate / -report) over the feature slices codesage maps. Shared global MCP, git hook installer.",
"version": "0.22.0",
"author": {
"name": "Ilia Alshanetsky",
"url": "https://github.com/iliaal"
},
"tags": [
"codesage",
"semantic-search",
"mcp",
"code-intelligence",
"retrieval",
"impact-analysis",
"code-review",
"feature-slices"
],
"source": "./plugins/codesage-tools"
}
]
}
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 · 34 lines scan A 72e81d67ca77
codesage is a plugin published in the GitHub repository iliaal/codesage (20 stars, last pushed 2d 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
repobrain
Plugin marketplace listing 1 plugin: repobrain.
repobrain
Repository knowledge engine plugin. Bundles CLI-backed slash commands (rb-setup / rb-init / rb-refresh / rb-ask) plus the agent-repo-init skill. Works in both Claude Code and Codex CLI.
codanna
Claude Code plugins for codanna, the code-intelligence CLI and MCP server: x-ray and graph views over a codanna index.
codanna-toolset
Codanna toolset for Claude Code: x-ray (semantic search + relationship traversal with 3D neighbourhood, radial tree and edge-bundle views) and graph (the whole index as a module disc with hubs at the centre, timeline and heatmap). Needs the codanna CLI.
open-codebase-index
Semantic code search and codebase graph tools for Claude Code.
helweg-plugins
Plugin marketplace listing 1 plugin: codebase-index.