setup

A setup wizard for AKA Security, which detects sensitive data locally and saves results in a local SQLite database. It reviews your real activity, can offer a scan of past activity, recommends a detection and notification posture, and applies changes after confirmation.

In plain words
What is it for?
Use it to onboard AKA Security, review past activity, calibrate notifications and detection settings, apply the recommendation, and continue to the dashboard.
Why use it?
It guides initial setup using your actual history instead of made-up examples. Some raw finding details and nearby transcript text are sent to the model API for judging false positives and severity, so this has a privacy consideration.

Command

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.

agentmods
npx agentmods add commands/akasecurity/ai-tc/setup
Clone the repo
git clone --depth 1 https://github.com/akasecurity/ai-tc
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 11,823 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.11823
Opus 5 $0.00009 $0.05912
Sonnet 5 $0.00003 $0.02365
Haiku 4.5 $0.00002 $0.01182

Measured 2d ago against content hash cd85739675d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

setup scanned grade B with 2 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.

Downloads and executes remote codemediumSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/akasecurity/ai-tc/bin-latest/tools/installer/install.sh | sh

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://raw.githubusercontent.com/akasecurity/ai-tc/bin-latest/tools/installer/install.sh | sh
plugins/claude-code/commands/setup.md · 895 lines

How it starts

The opening of the file, as written. The whole thing — 895 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AKA setup wizard

You are onboarding the AKA Security plugin for this machine. AKA works fully locally with zero backend and zero Docker: detection runs in-process and findings persist to a local SQLite store at ~/.aka/data/aka.db.

This wizard tells a calibration story: introduce AKA → show what it does → offer one retroactive scan → report the real numbers it found and the posture it recommends → apply on confirmation → show the installed summary → hand off to the dashboard. Everything the user sees is derived from their actual history — never a fabricated or demo number. When there isn't enough history to judge, the wizard falls back to a conservative severity-derived floor instead of guessing.

The false-positive/severity judgment needs the raw (unmasked) findings to rate them accurately, so it sends them to the model API through separate claude CLI subprocesses (a large history is judged in several batches). Per finding it sends the raw value; about 120 characters of the surrounding transcript text on either side of it, re-scanned first so every secret AKA's rules detect in that window is masked — including the finding's own value where it appears there, which leaves the raw value itself as the only raw text that crosses; and the finding's non-sensitive labels (rule id, category, severity, the masked value, the confidence score, and a counter the model echoes back). The source transcript's path never crosses. Those subprocesses ask the claude CLI to write no transcript, so the raw values do not enter this conversation or your scannable history — but a copy of them does leave the machine, sent to the model provider like any other Claude prompt. You act only on the raw-free plan the subprocesses print back.

That send takes two separate consents, collected at two different points and neither implying the other: the historical-read grant in step 1 (may AKA read past transcripts at all) and the model-judge grant in step 3 (may what it found be sent to the model API). Each is stated plainly before its own picker, and the judge refuses to run without the step-3 grant. The vault grant in step 1b is a third, separate question about local custody — it authorizes no send, and nothing about it changes what leaves the machine.

Follow the steps below in order. Nothing is written to the policy store until step 5 (or a floor fallback in step 3 if the calibration can't complete).

Read the full file on GitHub · 895 lines

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 First seen · 895 lines · 17 tokens per session scan B cd85739675d1

Subscribe to this mod's changes

setup is a command published in the GitHub repository akasecurity/ai-tc (10 stars, last pushed 4d ago), licensed Apache-2.0. It adds 17 tokens to every session and 11,823 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.