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/GhostlyGawd/codewebWrote 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/ghostlygawd/codeweb/codeweb)<a href="https://agentmods.dev/plugins/ghostlygawd/codeweb/codeweb"><img src="https://agentmods.dev/badge/plugins/ghostlygawd/codeweb/codeweb/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/ghostlygawd/codeweb/codeweb"><img src="https://agentmods.dev/badge/plugins/ghostlygawd/codeweb/codeweb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
codeweb 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 14d 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": "codeweb",
"version": "0.16.0",
"description": "See what your AI edits affect. Structural checks for AI code changes. Local call/import graphs and 28 MCP tools for impact, callers, and duplication. No LLM in the checks.",
"author": {
"name": "GhostlyGawd",
"email": "[email protected]"
},
"homepage": "https://github.com/GhostlyGawd/codeweb",
"repository": "https://github.com/GhostlyGawd/codeweb",
"hooks": "./hooks/hooks.json",
"mcpServers": {
"codeweb": {
"command": "node",
"args": [
"${CLAUDE_PLUGIN_ROOT}/scripts/mcp-server.mjs"
]
}
},
"keywords": [
"codebase-analysis",
"dependency-graph",
"call-graph",
"architecture",
"duplication",
"refactoring",
"domain-mapping",
"code-review",
"visualization"
],
"license": "MIT"
}
What it installs
The manifest is a name and a version. 3 skills, 4 commands, 2 agents, 3 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 596 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill codebase-anatomy A 136 tokens
- Skill release-tag A 80 tokens
- Skill codeweb A 41 tokens
- Command codeweb A 48 tokens
- Command codeweb-apply A 52 tokens
- Command codeweb-pitch A 45 tokens
- Command codeweb-narrate A 51 tokens
- Agent codeweb-dissector A 76 tokens
- Agent codeweb-domain-mapper A 67 tokens
- Hook PostToolUse A not measured
- Hook PreToolUse A not measured
- Hook SessionStart A not measured
- MCP server codeweb A not measured
What ships with it
1 file beside plugin.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.
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.
- 14d ago Changed ccdddf301c88
- 1mo ago Changed cebf5ff52608
- 1mo ago Changed 531a8d7ec85d
- 1mo ago Changed 53c22b750950
- 1mo ago First seen · 33 lines scan A 034569b51875
codeweb is a plugin published in the GitHub repository GhostlyGawd/codeweb (0 stars, last pushed 4d 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
code-graph-mcp
AST knowledge graph for intelligent code navigation — auto-indexes your codebase and provides semantic search, call graph traversal, HTTP route tracing, and impact analysis via MCP tools.
dekko
Static code map for LLM agents. /map parses the repository with tree-sitter into MAP.md and map.json (every file, function, signature, type, and call edge) without spending model tokens; an 18-tool MCP server (searchcode, outline, querysymbol, getcallers, workset, impactedtests, ...) answers structural questions fr.
analyze
Brownfield codebase audit: architecture, tech debt, security, and performance, distilled into a comprehensive Markdown report with an improvement roadmap.
debugger
Log-driven debugging workflow: insert logs, pinpoint the root cause, fix, verify, and clean up. --pw mode auto-reproduces web UI bugs via a bundled Playwright MCP. Supports JS/TS, Python, Java, and Kotlin.
dive-deeper
Deep-dive analysis skill for planning phase — trace execution paths, find related code, surface edge cases and potential problems.
meeba-brain
Ground-truth code graph context for your own private codebase — exact callers, callees, symbol definitions, and file dependencies, from a real parsed graph, not text-similarity guessing.