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-intent)<a href="https://agentmods.dev/skills/freespirits/claudeguard-il/cg-intent"><img src="https://agentmods.dev/badge/skills/freespirits/claudeguard-il/cg-intent.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 | $0.00078 | $0.04283 |
| Opus 5 | $0.00039 | $0.02142 |
| Sonnet 5 | $0.00016 | $0.00857 |
| Haiku 4.5 | $0.00008 | $0.00428 |
Grade A, and why
cg-intent 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 — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cg-intent — ask the app's owner what the app is supposed to permit
Every other check in ClaudeGuardIL asks a question the code answers by itself: is RLS on, is the key behind a public prefix. This one asks a question the code cannot answer — what is this app supposed to permit? "User A can read user B's order" is a critical bug in a store and a deliberate feature in an admin console: byte-identical code, opposite verdicts.
So the tool proposes, and the user confirms. That confirmation is the entire difference between
guessing and reviewing, and it is the only thing this skill produces. See
${CLAUDE_PLUGIN_ROOT}/skills/claudeguard/references/methodology/business-logic.md.
Argument: $ARGUMENTS — the repo path to interview about (default: the current repo root).
The two hard constraints
You may write EXACTLY ONE path: claudeguard.intent.yml at the scanned repo's root. No other
file, ever — not a scratch model dump inside their tree, not a backup copy, not a README note. Put
any working files in a scratch directory outside the repo and delete them. A skill that interviews
someone about their security model and then leaves extra files in their working tree has spent trust
it cannot earn back.
The ceiling: every business-logic finding is capped at confidence likely and can never be
confirmed. A multiple-choice answer is not a proof — the user may have misread the question, and
the code check against their answer may still be wrong. grader.mjs asserts the cap at module load.
Say this to the user in step 5, in one sentence, so a confirmed intent is not mistaken for a proof
of correctness. What confirming buys is that the checks run against their rules instead of the
tool's guess — that is real, and it is bounded.
Step 0 — preflight, and two places you must STOP
Run the engine and read the table facts:
node ${CLAUDE_PLUGIN_ROOT}/scripts/project_model.mjs <path> > <scratch>/cg-model.json
Read database.tables[] from it: each entry has name, columns[].name, and columnsKnownFrom.
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 · 300 lines · 78 tokens per session scan A b570cd5750e4
cg-intent is a skill published in the GitHub repository Freespirits/claudeguard-il (2 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 4,283 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…