A connection procedure for linking AgentKeeper to an AgentKeeper account. It supports a browser-based approval flow or a supplied API key, then installs hooks so Claude Code can send activity events to the AgentKeeper service.

Connecting an account, configuring API-key authentication for CI or managed computers, and installing the required Claude Code hooks.

It explains how to authenticate the tool and enable its monitoring connection on a workstation or in automated environments.

connect — Skill for Claude Code by rad-security/claude-code-plugin

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.

Any agent

npx skills add rad-security/claude-code-plugin --skill connect

Clone the repo

git clone --depth 1 https://github.com/rad-security/claude-code-plugin

Made for: Claude Code.

Or install agentkeeper, the plugin that ships this one along with the rest of its 13 skills, 4 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rad-security/claude-code-plugin/connect/github.svg)](https://agentmods.dev/skills/rad-security/claude-code-plugin/connect)

Your own site

<a href="https://agentmods.dev/skills/rad-security/claude-code-plugin/connect"><img src="https://agentmods.dev/badge/skills/rad-security/claude-code-plugin/connect/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rad-security/claude-code-plugin/connect"><img src="https://agentmods.dev/badge/skills/rad-security/claude-code-plugin/connect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,087 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 3 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00063	$0.06087
Opus 5.5	$0.00025	$0.02435
Sonnet 5.5	$0.00013	$0.01217
Haiku 4.5	$0.00006	$0.00609

Measured 2mo ago against content hash 7443542e545b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

connect scanned grade C with 3 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 2mo 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 600 "$AGENTKEEPER_DIR/api_key"

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep -q 'agentkeeper\.dev' "$HOME/.claude/settings.json" 2>/dev/null && echo "HOOKS_EXIST" || echo "NO_HOOKS"

Makes network callslowCapability

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

HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" --max-time 10 \

plugins/agentkeeper/skills/connect/SKILL.md · 597 lines

How it starts

The opening of the file, as written. The whole thing — 597 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentKeeper Connect

You are helping the user connect the AgentKeeper plugin to their www.agentkeeper.dev account. There are two paths:

Interactive (default): device-code browser flow. Open a URL, user approves in browser, we receive the key and install hooks.
Headless (--api-key <key>): user supplies an existing API key inline. Validate it server-side, store, install hooks. No browser, no prompts. Required for CI, fleet provisioning (Kanji / Ontra), and SSO-managed laptops where the browser flow is blocked.

After either path succeeds, HTTP hooks are installed into ~/.claude/settings.json so Claude Code natively sends hook events to the AgentKeeper API.

Step 0: Parse Arguments

Check the user's slash command invocation for flags:

If the invocation is /agentkeeper:connect --api-key <KEY> or /agentkeeper:connect --api-key=<KEY>: take the headless path (Step 1B). The <KEY> value is the raw API key string. Never echo it.
Otherwise: take the interactive path (Step 1 onward, existing flow).

If --api-key is present but no value follows, print:

The --api-key flag requires a value. Usage:
  /agentkeeper:connect --api-key ak_live_...

Generate a key at https://www.agentkeeper.dev/settings#api-keys

and stop.

Step 1B: Headless --api-key path

Validate the key against the health endpoint. Display a brief message while the request is in flight (do NOT echo the key itself):

AGENTKEEPER_DIR="$HOME/.agentkeeper-plugin"
[ -n "$CLAUDE_PLUGIN_DATA" ] && AGENTKEEPER_DIR="$CLAUDE_PLUGIN_DATA"
mkdir -p "$AGENTKEEPER_DIR"
HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" --max-time 10 \
  "https://www.agentkeeper.dev/api/v1/claude-code/health" \
  -H "Authorization: Bearer PASTE_KEY_HERE")
echo "$HTTP_CODE"

Replace PASTE_KEY_HERE with the value from the --api-key arg. Do NOT print the key in any output.

If the HTTP status is not 200:

That API key did not validate. www.agentkeeper.dev returned HTTP [status].

Common causes:
  - Key was revoked or belongs to a deleted org
  - Typo or extra whitespace in the pasted value
  - Wrong environment (staging key vs prod)

Generate a fresh key at https://www.agentkeeper.dev/settings#api-keys

Stop. Do NOT write the key to disk.

Read the full file on GitHub · 597 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.

2mo ago First seen · 597 lines · 63 tokens per session scan C 7443542e545b

Subscribe to this mod's changes

connect is a skill published in the GitHub repository rad-security/claude-code-plugin (3 stars, last pushed 23d ago), licensed MIT. It adds 63 tokens to every session and 6,087 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 3 findings (asks for root, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents

connect next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
connectrad-security/claude-code-plugin	Skill	3	23d ago	MIT	C	63	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

connect