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.
npx agentmods add skills/rad-security/claude-code-plugin/disconnectnpx skills add rad-security/claude-code-plugin --skill disconnectgit clone --depth 1 https://github.com/rad-security/claude-code-pluginWhat 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 | $0.00035 | $0.00637 |
| Opus 5 | $0.00017 | $0.00318 |
| Sonnet 5 | $0.00007 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade B, and why
disconnect scanned grade B with 1 finding 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.
- Remove AgentKeeper hooks from ~/.claude/settings.json How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentKeeper Disconnect
You are helping the user remove AgentKeeper hooks and disconnect from their account.
Step 1: Confirm
Display:
This will:
- Remove AgentKeeper hooks from ~/.claude/settings.json
- Delete your stored API key
Local detection via the plugin will still work.
Run /agentkeeper:connect to reconnect later.
Proceed? (y/n)
If the user declines, stop.
Step 2: Remove hooks and key
Run:
python3 << 'PYEOF'
import json, os
settings_path = os.path.expanduser("~/.claude/settings.json")
api_key_path = os.path.expanduser("~/.agentkeeper-plugin/api_key")
removed_hooks = False
removed_key = False
# Remove hooks from settings.json
if os.path.isfile(settings_path):
try:
with open(settings_path) as f:
settings = json.load(f)
hooks = settings.get("hooks", {})
changed = False
for event_name in list(hooks.keys()):
existing = hooks[event_name]
cleaned = []
for group in existing:
sub_hooks = group.get("hooks", [])
if any("www.agentkeeper.dev" in (h.get("url") or "") for h in sub_hooks):
changed = True
continue
cleaned.append(group)
if cleaned:
hooks[event_name] = cleaned
else:
del hooks[event_name]
changed = True
if not hooks and "hooks" in settings:
del settings["hooks"]
changed = True
if changed:
with open(settings_path, "w") as f:
json.dump(settings, f, indent=2)
f.write("\n")
removed_hooks = True
except (json.JSONDecodeError, KeyError):
pass
# Delete API key
if os.path.isfile(api_key_path):
os.remove(api_key_path)
removed_key = True
if removed_hooks:
print("HOOKS_REMOVED")
if removed_key:
print("KEY_REMOVED")
if not removed_hooks and not removed_key:
print("NOTHING_TO_REMOVE")
PYEOF
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.
- yesterday First seen · 108 lines · 35 tokens per session scan B d5227d3d2ee8
disconnect is a skill published in the GitHub repository rad-security/claude-code-plugin (2 stars, last pushed 26d ago), licensed MIT. It adds 35 tokens to every session and 637 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…