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/mirnoorata/codexaWrote 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/mirnoorata/codexa/claude-code)<a href="https://agentmods.dev/plugins/mirnoorata/codexa/claude-code"><img src="https://agentmods.dev/badge/plugins/mirnoorata/codexa/claude-code/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/mirnoorata/codexa/claude-code"><img src="https://agentmods.dev/badge/plugins/mirnoorata/codexa/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
codexa 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.
This is a copy
86% identical to codexa-integrations marketplace — 29 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"name": "codexa",
"version": "0.20.1",
"description": "Codexa for Claude Code. MCP server exposes evidence-backed repo context tools; SessionStart injects repo context, PreToolUse saves an implicit pre-edit baseline, Stop runs the post-edit drift review and surfaces blocking drift to the model. Slash commands wrap the codexa CLI.",
"author": {
"name": "Codexa"
},
"keywords": [
"codexa",
"context",
"impact",
"edit-safety",
"drift-review",
"mcp"
]
}
What it installs
The manifest is a name and a version. 6 commands, 3 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 77 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Command codexa-review A 12 tokens
- Command codexa-plan A 11 tokens
- Command codexa-brief A 15 tokens
- Command codexa-impact A 18 tokens
- Command codexa-prove A 12 tokens
- Command codexa-status A 9 tokens
- Hook SessionStart A not measured
- Hook Stop A not measured
- Hook PreToolUse A not measured
- MCP server codexa 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.
- 14d ago Changed 383c9c271bbf
- 26d ago Changed 4d5546d214ec
- 29d ago Changed ce245b28ca8e
- 1mo ago First seen · 17 lines scan A 29daa0fa429e
codexa is a plugin published in the GitHub repository mirnoorata/codexa (2 stars, last pushed 5d 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. It is 86% identical to codexa-integrations marketplace, differing in 29 lines, and is treated as a copy.
Other plugins, from other repositories
ai-sdlc
AI-SDLC governance framework for Claude Code — action enforcement, telemetry, quality gates, and review 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.
mattpocock-skills
Skills adapted from Matt Pocock's public collection.
codesage-tools
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.
loki-mode
Autonomous spec-to-product build system with a built-in trust layer (RARV-C closure loop, 8 quality gates, completion council). Ships Loki's spec-hardening, drift-detection, and deterministic PR verification commands plus the Loki MCP server.
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…