detections

detections is a command for Claude Code from akasecurity/ai-tc. It costs 11 tokens per session (319 once invoked), scanned A, original, Apache-2.0.

A read-only inventory of AKA’s installed detection packs, including their versions, rule counts, enabled state, enforcement policy, and available updates.

In plain words
What is it for?
Use it to review detection-pack configuration and update availability. Updates must be run separately in a terminal.
Why use it?
It shows exactly which rule collections are running and whether newer versions exist, without changing your setup.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the aka plugin — 10 commands, 8 hooks shipped together

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

Made for: Claude Code.

Or install aka, the plugin that ships this one along with the rest of its 10 commands, 8 hooks.

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 detections

README.md
[![agentmods](https://agentmods.dev/badge/commands/akasecurity/ai-tc/detections.svg)](https://agentmods.dev/commands/akasecurity/ai-tc/detections)
Your own site
<a href="https://agentmods.dev/commands/akasecurity/ai-tc/detections"><img src="https://agentmods.dev/badge/commands/akasecurity/ai-tc/detections.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 319 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 5.1 $0.00011 $0.00319
Opus 5 $0.00005 $0.00160
Sonnet 5 $0.00002 $0.00064
Haiku 4.5 $0.00001 $0.00032

Measured 5d ago against content hash 8deebe87cc2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

detections 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 5d 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/commands/detections.md · 31 lines

What it actually says

AKA detections

Run the read script and show the user its output exactly as printed. The script already prints its content inside a Markdown code fence — reproduce that verbatim and do not add another code fence, strip the fence, or reformat it. The fence is required: it is a space-aligned monospace table that Markdown would otherwise collapse. Do not reformat the columns or restate each row.

node "${CLAUDE_PLUGIN_ROOT}/scripts/query.js" detections

This lists the detection packs installed in ~/.aka/data/aka.db — one row per pack with its installed version, the latest version this plugin ships, rule count, enabled state, assigned enforcement policy, and whether an update is available. These packs are what the plugin actually scans with.

Detection updates are never applied automatically — a plugin upgrade only records what's newly available; the installed packs keep running unchanged until the user updates them. This command is strictly read-only: do not apply, enable, disable, or re-policy a detection from here. If the user wants to update, tell them to run one of these themselves in a terminal:

  • aka detections update --all — update every pack
  • aka detections update <pack-id> — update one pack
  • aka dashboard → Detections → Update — review and apply in the dashboard
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. 5d ago First seen · 31 lines · 11 tokens per session scan A 8deebe87cc2c

Subscribe to this mod's changes

detections is a command published in the GitHub repository akasecurity/ai-tc (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 11 tokens to every session and 319 once invoked, about $0.0001 per session on Opus 5. 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.