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-scan)<a href="https://agentmods.dev/skills/freespirits/claudeguard-il/cg-scan"><img src="https://agentmods.dev/badge/skills/freespirits/claudeguard-il/cg-scan/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-scan"><img src="https://agentmods.dev/badge/skills/freespirits/claudeguard-il/cg-scan.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 | $0.00073 | $0.03945 |
| Opus 5 | $0.00036 | $0.01972 |
| Sonnet 5 | $0.00015 | $0.00789 |
| Haiku 4.5 | $0.00007 | $0.00394 |
Grade A, and why
cg-scan 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 8d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cg-scan — static security scan (Tier 0)
Run a safe, read-only static audit. No network, no credentials. This is the default entry point.
Arguments: $ARGUMENTS — optional path to scan (default: repo root) and an optional --domain
filter. --domain narrows which auditors you dispatch and which catalogs you read; it does not
narrow the grader, which always grades the whole model so coverage still adds up.
The pipeline
Engine → Facts → Grader → Findings → Auditors add reviewer findings → Report
| Stage | Who | What it is allowed to do |
|---|---|---|
| Engine | scripts/project_model.mjs |
Emits Facts: routes, tables, env vars, LLM sites, clients, the client/server boundary. Has no opinion about danger. |
| Grader | scripts/grader.mjs |
The single authority on severity and confidence. Turns Facts into Findings and builds the coverage ledger. |
| Auditors | web-auditor, ai-auditor, mobile-auditor, infra-auditor |
Add findings with provenance: 'reviewer' and evidence: 'judgement' — capped at confidence likely, never confirmed. |
| Verifier | finding-verifier |
Refutes only — removes a finding by naming the fact that disproves it. It never edits a confidence, never lowers a severity, never adds findings. |
| Report | you | Render what the grader produced. |
You do not grade. Not while reading a file, not while writing the report, not "just this once
because it looks worse than P2". Severity being reproducible — the same repo grading the same way
every time — is the entire public claim of this tool. The moment you re-derive it from a check
document, two runs of /cg-scan on one repo disagree, and every conversation about a finding turns
into a conversation about the model.
Concretely:
- Severity and confidence come from
grader.mjsand nowhere else. Confidence is a pure function of evidence strength (definitive→confirmed,strong→likely,weak→needs-review,judgement→likely). Never hand-set it, never "upgrade" one. - Auditors add judgement findings, which is the work no rule can do — auth that is present and
does not enforce, ownership filtered on the wrong column, a workflow step that can be skipped.
They are capped at
likelybecause no amount of reading is a proof. - You render. Titles, ordering, coverage, both languages.
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.
- 8d ago First seen · 237 lines · 73 tokens per session scan A 74850f804ed5
cg-scan is a skill published in the GitHub repository Freespirits/claudeguard-il (2 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 3,945 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…