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/iliaal/codesageWrote 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/iliaal/codesage/codesage-tools)<a href="https://agentmods.dev/plugins/iliaal/codesage/codesage-tools"><img src="https://agentmods.dev/badge/plugins/iliaal/codesage/codesage-tools/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/iliaal/codesage/codesage-tools"><img src="https://agentmods.dev/badge/plugins/iliaal/codesage/codesage-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
codesage-tools 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-tools",
"version": "0.43.0",
"description": "Claude Code integration for CodeSage, a Rust-based code intelligence engine. Slash commands for onboarding (init + index + global MCP registration + git hooks + agent hint), reset, incremental reindex with model-mismatch cleanup, retrieval benchmarking, and a subagent-driven review workflow that fans out feature-slice reviews in parallel and persists findings to `.codesage/findings/`. A single global MCP server serves every onboarded project, routed by an absolute `project` argument on each call.",
"author": {
"name": "Ilia Alshanetsky",
"url": "https://github.com/iliaal"
},
"license": "MIT",
"keywords": [
"codesage",
"semantic-search",
"mcp",
"code-intelligence",
"retrieval",
"impact-analysis",
"agent-tools",
"code-review",
"feature-slices"
]
}
What it installs
The manifest is a name and a version. 1 skill, 10 commands, 2 agents, 1 hook travel with it, and installing the plugin installs all of them — 316 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill codesage-retrieval A 45 tokens
- Command codesage-review A 16 tokens
- Command codesage-revalidate A 17 tokens
- Command codesage-reset A 29 tokens
- Command codesage-triage A 26 tokens
- Command codesage-eval A 24 tokens
- Command codesage-onboard A 28 tokens
- Command codesage-report A 18 tokens
- Command codesage-bench A 25 tokens
- Command codesage-reindex A 28 tokens
- Command codesage-prompt-override A 19 tokens
- Agent codesage-feature-reviewer A 19 tokens
- Agent codesage-finding-verifier A 22 tokens
- Hook PreToolUse 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.
- 2d ago Changed 23dcb2f71c13
- 6d ago Changed a42e87dbced4
- 11d ago Changed c5200201c160
- 13d ago Changed 010538360e61
- 14d ago Changed 73aa541dd0a8
- 16d ago Changed d1e20e9895b8
- 20d ago Changed 30332e0b36a9
- 21d ago Changed 8b85e6b8271d
- 25d ago Changed 4639eac66fe4
- 1mo ago First seen · 22 lines scan A dc260db75c4d
codesage-tools is a plugin published in the GitHub repository iliaal/codesage (21 stars, last pushed yesterday), 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
memtrace-skills
Memtrace skills for codebase exploration, code search, relationship analysis, temporal evolution, blast radius impact, code quality, graph algorithms, API topology, GitHub PR code review, multi-agent fleet coordination (branch-scoped intents, conflict classification, and agent-judged Class C resolution), and…
sverklo-skill
Teaches Claude how to use sverklo's code intelligence MCP tools — semantic search, blast-radius, PR review, codebase audit, persistent memory.
codebase-index
Semantic code search and codebase graph tools for Claude Code.
mattpocock-skills
Skills adapted from Matt Pocock's public collection.
kin
Kin keeps a living map of the software itself so humans and agents can understand what every change touches. Locate, search, context packs, data-flow tracing, and impact analysis without raw file search.
rtfm
The open retrieval layer for AI agents — indexes code, docs, data. Search via MCP.