status

A status check for AgentKeeper, a tool that monitors coding-agent activity. It reports whether protection is running locally or through a connection, how alerts are delivered, threat statistics, and workstation details.

In plain words
What is it for?
Use it to inspect AgentKeeper's operating mode, hook setup, alert statistics, and workstation information.
Why use it?
It gives you a quick view of whether AgentKeeper is active and what it has detected. This can reveal connection or monitoring problems before you rely on it.

Skill for Claude CodeCodex

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 skills/rad-security/claude-code-plugin/status
Any agent
npx skills add rad-security/claude-code-plugin --skill status
Clone the repo
git clone --depth 1 https://github.com/rad-security/claude-code-plugin

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,184 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 $0.00040 $0.01184
Opus 5 $0.00020 $0.00592
Sonnet 5 $0.00008 $0.00237
Haiku 4.5 $0.00004 $0.00118

Measured yesterday against content hash b0f5583f63a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

status 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 yesterday.

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.

Reads agent configuration directoriesmediumAgent snooping

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

if grep -q 'agentkeeper\.dev' "$HOME/.claude/settings.json" 2>/dev/null; then

Makes network callslowCapability

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

curl -s --max-time 5 "https://www.agentkeeper.dev/api/v1/claude-code/health" \
plugins/agentkeeper/skills/status/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentKeeper Status

You are showing the current AgentKeeper shield status. Determine the mode and display the appropriate information.

Step 1: Determine Mode

Check for API key

AGENTKEEPER_DIR="$HOME/.agentkeeper-plugin"
[ -n "$CLAUDE_PLUGIN_DATA" ] && AGENTKEEPER_DIR="$CLAUDE_PLUGIN_DATA"
cat "$AGENTKEEPER_DIR/api_key" 2>/dev/null

If a key is found and non-empty, the user is in connected mode. Otherwise, local mode.

Determine hook delivery method

Run:

HOOK_SOURCE="plugin"
if grep -q 'agentkeeper\.dev' "$HOME/.claude/settings.json" 2>/dev/null; then
  HOOK_SOURCE="user_http"
fi
for f in ".claude/settings.json" ".claude/settings.local.json"; do
  if [ -f "$f" ] && grep -q 'agentkeeper\.dev' "$f" 2>/dev/null; then
    HOOK_SOURCE="repo_http"
    break
  fi
done
echo "HOOK_SOURCE:$HOOK_SOURCE"

Capture the value after HOOK_SOURCE: for use in the status output.

Step 2: Display Status

Local Mode

Read local stats:

AGENTKEEPER_DIR="$HOME/.agentkeeper-plugin"
[ -n "$CLAUDE_PLUGIN_DATA" ] && AGENTKEEPER_DIR="$CLAUDE_PLUGIN_DATA"
cat "$AGENTKEEPER_DIR/nudge_state.json" 2>/dev/null

If the nudge state file exists, parse total_blocks, nudges_shown, and any session counters. If it does not exist, use defaults (0 blocks, no sessions recorded).

Also read the config for detection mode:

AGENTKEEPER_DIR="$HOME/.agentkeeper-plugin"
[ -n "$CLAUDE_PLUGIN_DATA" ] && AGENTKEEPER_DIR="$CLAUDE_PLUGIN_DATA"
cat "$AGENTKEEPER_DIR/config.json" 2>/dev/null

Display:

AgentKeeper Shield Status

Mode: Local (no account connected)
Detection: [warn|block] mode
Shield: Active — using bundled threat patterns
Hooks: [if user_http: "User-level HTTP hooks (full coverage)" | if repo_http: "Repo-level HTTP hooks (full coverage)" | if plugin: "Plugin hooks only (limited — run /agentkeeper:connect to upgrade)"]

Session Stats:
  Total threats detected: [total_blocks or 0]
  Sessions tracked: [count or "current session"]
  Nudges shown: [nudges_shown or 0]

Local mode includes:
  - 12 critical/high threat patterns
  - Credential exfiltration detection
  - Reverse shell detection
  - System file write protection

Connect a free account for:
  - Full 24+ pattern detection engine
  - Dashboard with threat feed and history
  - Scan result tracking
  - Setup audit trends

Run /agentkeeper:connect to link your free account.

Read the full file on GitHub · 148 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. yesterday First seen · 148 lines · 40 tokens per session scan B b0f5583f63a9

Subscribe to this mod's changes

status is a skill published in the GitHub repository rad-security/claude-code-plugin (2 stars, last pushed 26d ago), licensed MIT. It adds 40 tokens to every session and 1,184 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens