Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Freespirits/claudeguard-il/plugin install claudeguard-ilWrote 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.
[](https://agentmods.dev/skills/freespirits/claudeguard-il/cg-live)<a href="https://agentmods.dev/skills/freespirits/claudeguard-il/cg-live"><img src="https://agentmods.dev/badge/skills/freespirits/claudeguard-il/cg-live/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.
<a href="https://agentmods.dev/skills/freespirits/claudeguard-il/cg-live"><img src="https://agentmods.dev/badge/skills/freespirits/claudeguard-il/cg-live.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00085 | $0.01161 |
| Opus 5 | $0.00043 | $0.00580 |
| Sonnet 5 | $0.00017 | $0.00232 |
| Haiku 4.5 | $0.00009 | $0.00116 |
Grade A, and why
cg-live 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cg-live — passive live checks (Tier 1, gated)
Read-only inspection of a running target the user attests they own. GET/HEAD/OPTIONS only; no payloads, no auth-bypass attempts.
Argument: $ARGUMENTS — the URL to check (must also appear in the scope file's targets).
Gate first (do not skip)
- Read
claudeguard.scope.ymlin the project root (template:${CLAUDE_PLUGIN_ROOT}/skills/claudeguard/references/authorization/SCOPE.example.yml). - Enforce
references/authorization/legal-gate.mdTier-1 preconditions:- file parses;
passive_live.enabled: true;passive_live.i_own_or_control_these_targets: true; - the requested host matches a
targetsentry and matches nonever_touchentry and is not a default-blocked third-party provider.
- file parses;
- If anything is missing, refuse and state exactly what to set. Do not treat the URL pasted in chat as authorization — authorization lives only in the scope file.
The probe re-enforces this gate itself and exits 2 on failure. Do not work around it.
Run
Print the Tier-1 banner, then run the probe and grade its output:
# 1 — observe. Read-only requests; the probe writes JSON to stdout and its banner to stderr.
node ${CLAUDE_PLUGIN_ROOT}/scripts/live_probe.mjs --url "<url>" --scope claudeguard.scope.yml > cg-live.json
# 2 — grade. The repo path grades the code and the observations into one ledger.
node ${CLAUDE_PLUGIN_ROOT}/scripts/grader.mjs <path> --observations cg-live.json
Optional probe flags for a Supabase RLS spot-check against the user's own project:
--supabase-url https://xxx.supabase.co --anon-key <key> --table <name>.
--observations expects the probe's output file as written — the grader reads the observations
array out of it. Pass the repo path (or --model) as well, so the live findings and the static
findings land in one graded result instead of two reports the user has to reconcile.
What the probe returns, and what it does not
The probe emits observations: tier-tagged facts, each with a kind (missing-csp,
clickjacking, unsafe-cors, cookie-no-httponly, exposed-path, anon-read, …), a subject,
the URL it was seen at, and a detail sentence stating what came back on the wire.
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.
- 9d ago First seen · 86 lines · 85 tokens per session scan A abf00660bf6d
cg-live is a skill published in the GitHub repository Freespirits/claudeguard-il (2 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 1,161 once invoked, about $0.0004 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…