easy-cheese-setup

easy-cheese-setup is a skill for Claude Code, Codex from paulnsorensen/easy-cheese. It costs 104 tokens per session (933 once invoked), scanned A, original, MIT.

A workflow for registering and repairing a durable searchable corpus and the current repository’s tenant. A corpus is a stored collection of research or specifications that can be searched across sessions.

In plain words
What is it for?
Running a report-only check or, after approval, creating or repairing the global corpus, registering the current repository, and diagnosing both setups.
Why use it?
It detects configuration drift and reports intended repairs before changing anything, helping keep shared and project-specific search data available.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 skills/easy-cheese-setup/scripts/easy-cheese-setup.pyz global [--apply] # durable-corpus registration/repair.

Part of the easy-cheese plugin — 18 skills shipped together

Good fit Running a report-only check or, after approval, creating or repairing the global corpus, registering the current repository, and diagnosing both setups.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/paulnsorensen/easy-cheese
agentmods
npx agentmods add skills/paulnsorensen/easy-cheese/easy-cheese-setup

Made for: Claude Code, Codex.

Or install easy-cheese, the plugin that ships this one along with the rest of its 18 skills.

Wrote 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.

agentmods badge for easy-cheese-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/paulnsorensen/easy-cheese/easy-cheese-setup/github.svg)](https://agentmods.dev/skills/paulnsorensen/easy-cheese/easy-cheese-setup)
Your own site
<a href="https://agentmods.dev/skills/paulnsorensen/easy-cheese/easy-cheese-setup"><img src="https://agentmods.dev/badge/skills/paulnsorensen/easy-cheese/easy-cheese-setup/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.

agentmods 80×15 button for easy-cheese-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/paulnsorensen/easy-cheese/easy-cheese-setup"><img src="https://agentmods.dev/badge/skills/paulnsorensen/easy-cheese/easy-cheese-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 933 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 38
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00104 $0.00933
Opus 5 $0.00052 $0.00466
Sonnet 5 $0.00021 $0.00187
Haiku 4.5 $0.00010 $0.00093

Measured yesterday against content hash 50d75c0c87f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

easy-cheese-setup 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 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.

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.

skills/easy-cheese-setup/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/easy-cheese-setup

Register the durable cheese-durable Hallouminate corpus. The corpus makes each project's XDG artifacts searchable across sessions.

Register the current repository as a Hallouminate tenant when the user requests it. This process is idempotent. It does not delete data.

The engine is a self-contained bundle at skills/easy-cheese-setup/scripts/easy-cheese-setup.pyz. It has three commands. Each command changes data only with --apply. Without this option, each command only reports.

python3 skills/easy-cheese-setup/scripts/easy-cheese-setup.pyz global [--apply]   # durable-corpus registration/repair
python3 skills/easy-cheese-setup/scripts/easy-cheese-setup.pyz local  [--apply]   # per-repository tenant registration
python3 skills/easy-cheese-setup/scripts/easy-cheese-setup.pyz doctor [--apply]   # both legs

At installation, install.sh calls global --apply when --mcp includes hallouminate. This skill controls the interactive process.

Flow

Run doctor without --apply first. It reports the planned actions for both legs without changes. Show the report as evidence. Ask the user for confirmation. Apply only the approved legs.

Global leg — durable corpus

  • Create the directory from paths.corpus_home() if it does not exist. This action prevents Hallouminate issue #101.
  • Insert or replace the marked [[corpus]] block in the Hallouminate configuration file.
  • Read config_path() for that file. Its default is ~/.config/hallouminate/config.toml.
  • HALLOUMINATE_CONFIG and XDG_CONFIG_HOME override that default. Do not assume the default path.
  • Use # >>> easy-cheese:cheese-durable as the start marker.
  • Use # <<< easy-cheese:cheese-durable as the end marker. Write the identifier in both markers.
  • An end marker without the identifier does not close the block. The rewrite then replaces the rest of the file.
  • Point the block at corpus_home(). A second global --apply leaves the file unchanged.
  • Use --apply to correct a marked block that points elsewhere.
  • Legacy migration requires user interaction. An unmarked cheese-global → ~/.cheese block is stale. Show the report. Ask the user for confirmation. Then use the explicit migration option. The installer never uses this option:

Read the full file on GitHub · 69 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. yesterday Changed 50d75c0c87f5
  2. 4d ago Changed · +22 lines · -29 tokens per session f223ecbfdc7f
  3. 11d ago First seen · 47 lines · 133 tokens per session scan A cc7f57f7a9a2

Subscribe to this mod's changes

easy-cheese-setup is a skill published in the GitHub repository paulnsorensen/easy-cheese (18 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 933 once invoked, about $0.0005 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 2026-08-30.