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-fix)<a href="https://agentmods.dev/skills/freespirits/claudeguard-il/cg-fix"><img src="https://agentmods.dev/badge/skills/freespirits/claudeguard-il/cg-fix.svg" alt="Measured on agentmods" 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 | $0.00074 | $0.01206 |
| Opus 5 | $0.00037 | $0.00603 |
| Sonnet 5 | $0.00015 | $0.00241 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
cg-fix 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cg-fix — apply guards (opt-in, dry-run first)
Apply the hardening code to the codebase. Safety-first and non-destructive by default: show a diff, get confirmation, then write. Never touches a live target — only source files.
Argument: $ARGUMENTS — a finding id or all (default: every eligible finding from the latest
grader run), plus optional --apply to write after review.
Eligibility — both conditions, no exceptions
A finding may be auto-fixed only if:
finding.confidence === 'confirmed' AND finding.autofixable === true
Neither field is yours to set. confirmed comes only from evidence.strength === 'definitive' —
the bundler inlines the prefix, the migration never enables RLS, the header was absent on the wire.
Everything else caps lower: strong → likely, weak → needs-review, and a reviewer's
judgement → likely and can never reach confirmed. So a reviewer finding is never eligible
here, however well argued. Editing someone's source on the strength of a guess is how a security
tool becomes the thing that broke production.
Skip everything else and say why in one line — "needs a human: the check may live in a helper this
pass does not follow" — with the finding's assumption, so the user knows what to check rather
than just that it was skipped.
The finding schema you are reading
grader.mjs emits, per finding:
guard—guard-recipes/<name>.md#<anchor>, resolved against${CLAUDE_PLUGIN_ROOT}/skills/claudeguard/references/. This is the fix. Open that anchor; do not invent a patch from the title.evidence— an object, not an array:{ strength, nameOnly, why, at: [...] }.evidence.at[]is the location list:{ file, line, snippet }per entry. This is where the patch goes.evidence.whyis the mechanism in one sentence — use it in the diff summary so the user reads why before approving a write.- Schema change from v1: evidence used to be the bare array that is now
evidence.at. Code or habits that reach forfinding.evidence[0].filenow getundefinedand will patch nothing, or the wrong file, without complaining.
severity,confidence,provenance,tier,assumption,id,subject— for grouping and for the summary. Never recompute any of them.
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 · 89 lines · 74 tokens per session scan A a1cb21310332
cg-fix is a skill published in the GitHub repository Freespirits/claudeguard-il (2 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 1,206 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…