agentmods.dev

aka

aka is a plugin for Claude Code from akasecurity/ai-tc. Its manifest loads nothing; the 10 commands, 8 hooks it bundles cost 109 tokens per session together, scanned A, original, Apache-2.0.

A Claude Code plugin for inspecting and governing AI prompts and tool activity. Its detection runs on your machine, and events are saved in a local SQLite database.

In plain words
What is it for?
Use it to apply AKA’s detection, enforcement, reporting, exception, and dashboard features in Claude Code.
Why use it?
It keeps detection and event records local while providing controls over AI traffic in Claude Code.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest. Also seen: mentions Claude Code.

not rated 11repo changed 2d ago A scan tokens not measured original Apache-2.0

Good fit Use it to apply AKA’s detection, enforcement, reporting, exception, and dashboard features in Claude Code.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add akasecurity/ai-tc
/plugin install aka
View source ↗ akasecurity/ai-tc akasecurity.io
Install

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.

Clone the repo
git clone --depth 1 https://github.com/akasecurity/ai-tc

Made for: Claude Code.

Wrote 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.

agentmods badge for aka

README.md
[![agentmods](https://agentmods.dev/badge/plugins/akasecurity/ai-tc/claude-code/github.svg)](https://agentmods.dev/plugins/akasecurity/ai-tc/claude-code)
Your own site
<a href="https://agentmods.dev/plugins/akasecurity/ai-tc/claude-code"><img src="https://agentmods.dev/badge/plugins/akasecurity/ai-tc/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.

agentmods 80×15 button for aka

Your own site · 80×15
<a href="https://agentmods.dev/plugins/akasecurity/ai-tc/claude-code"><img src="https://agentmods.dev/badge/plugins/akasecurity/ai-tc/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 10 commands, 8 hooks cost 109 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

aka 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.

plugins/claude-code/.claude-plugin/plugin.json · 9 lines

What it actually says

{
  "name": "aka",
  "version": "0.9.19",
  "description": "AI Traffic Control — inspect and govern AI prompts in Claude Code. Detection runs locally; events are recorded to a local SQLite store on your machine.",
  "homepage": "https://github.com/akasecurity/ai-tc",
  "author": { "name": "AKA Security" },
  "types": "./types/index.d.ts"
}
Contents

What it installs

The manifest is a name and a version. 10 commands, 8 hooks travel with it, and installing the plugin installs all of them — 109 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

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.

  1. 2d ago Changed 021794286f94
  2. 3d ago Changed 865d3960b4a7
  3. 5d ago Changed · +1 lines 8fc51b10eb67
  4. 9d ago Changed 9af0b85f275f
  5. 14d ago Changed 545d6eb63b8b
  6. 22d ago Changed 0f4032ea5b9b
  7. 1mo ago Changed 4b6d713ba9b3
  8. 1mo ago Changed a6d0fb5f6935
  9. 1mo ago Changed 603fb4a6cd6f
  10. 1mo ago First seen · 8 lines scan A e5f25cdf83e4

Subscribe to this mod's changes

aka is a plugin published in the GitHub repository akasecurity/ai-tc (11 stars, last pushed today), 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.

Claude CodeSecurityagentsaiclaudeclaude-code-pluginharness-ai
Related

Other plugins, from other repositories

sage

Safety for Agents - Agent Detection & Response (ADR) for AI agents.

gendigitalinc/sage · not measured

ocr

Shift code review quality gates left with customizable multi-agent review. Define your reviewer team composition, run parallel reviews with redundancy, and let reviewers debate findings before synthesis. Works with specs, proposals, and project standards.

spencermarx/open-code-review · not measured

dotnet-pilot

.NET development plugin for Claude Code — Roslyn semantic analysis, DI/architecture/EF Core guards, convention-aware scaffolding, TDD agents, security and performance review, and project lifecycle commands.

zdanovichnick/dotnet-pilot · not measured

software-factory

Lanes, tickets, and a human merge. Same skills as Cursor, Grok, and Codex.

Kripu77/software-factory · not measured

claude-teammates

Fleet orchestration, worktree-isolated parallel execution, automated phase gates, and supervision for Claude Code teammates.

andreymudri/claude-teammates · not measured

dinf

D∞ — the ⟨parts | Ω⟩ shape every durable teaching, framework, plan, and joke has, as a working toolchain: an agent embodied in a directory, three operators (FACTOR / ADJOIN / CHRISTEN), and a gate that catches a missing closure at the syntax level.

sancovp/dinf · not measured