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/R1ck29/claude-code-codegraph-harnessWrote 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/r1ck29/claude-code-codegraph-harness/codegraph-evaluator)<a href="https://agentmods.dev/plugins/r1ck29/claude-code-codegraph-harness/codegraph-evaluator"><img src="https://agentmods.dev/badge/plugins/r1ck29/claude-code-codegraph-harness/codegraph-evaluator/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/r1ck29/claude-code-codegraph-harness/codegraph-evaluator"><img src="https://agentmods.dev/badge/plugins/r1ck29/claude-code-codegraph-harness/codegraph-evaluator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
codegraph-evaluator 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 2mo 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": "codegraph-evaluator",
"displayName": "Codegraph Evaluator",
"version": "0.2.0-rc.1",
"description": "Claude Code routing and source verification for the approved local read-only codegraph gateway.",
"author": {
"name": "R1ck29"
},
"homepage": "https://github.com/R1ck29/claude-code-codegraph-harness",
"repository": "https://github.com/R1ck29/claude-code-codegraph-harness",
"license": "Apache-2.0",
"keywords": ["code-graph", "mcp", "evaluation", "code-intelligence"]
}
What it installs
The manifest is a name and a version. 1 skill, 1 agent travel with it, and installing the plugin installs all of them — 46 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 2mo ago First seen · 14 lines scan A 4bf4fad51bcc
codegraph-evaluator is a plugin published in the GitHub repository R1ck29/claude-code-codegraph-harness (0 stars, last pushed 14d 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 2026-08-31.
codegraph-evaluator compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| codegraph-evaluatorR1ck29/claude-code-codegraph-harness | Plugin | 0 | 14d ago | Apache-2.0 | A | — | Claude Code |
| codebase-memoryDeusData/codebase-memory-mcp | Plugin | 49k | yesterday | MIT | A | — | Claude Code |
| boutiquemergesort/Boutique | Plugin | 1.1k | 2d ago | MIT | A | — | Claude Code |
| mattpocock-skillsmrclrchtr/supi | Plugin | 104 | today | MIT | A | — | Claude Code |
| jmunch marketplacejgravelle/jcodemunch-mcp | Plugin | 2.9k | today | none | A | — | Claude Code |
| narsilpostrv/narsil-mcp | Plugin | 188 | 1mo ago | Apache-2.0 | A | — | Claude Code |
| codesage-toolsiliaal/codesage | Plugin | 21 | today | MIT | A | — | Claude Code |