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.
git clone --depth 1 https://github.com/paulnsorensen/easy-cheesenpx agentmods add skills/paulnsorensen/easy-cheese/easy-cheese-setupWrote 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/paulnsorensen/easy-cheese/easy-cheese-setup)<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.
<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>- NVIDIA SkillSpector warn
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.
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 | $0.00104 | $0.00933 |
| Opus 5 | $0.00052 | $0.00466 |
| Sonnet 5 | $0.00021 | $0.00187 |
| Haiku 4.5 | $0.00010 | $0.00093 |
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.
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_CONFIGandXDG_CONFIG_HOMEoverride that default. Do not assume the default path.- Use
# >>> easy-cheese:cheese-durableas the start marker. - Use
# <<< easy-cheese:cheese-durableas 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 secondglobal --applyleaves the file unchanged. - Use
--applyto correct a marked block that points elsewhere. - Legacy migration requires user interaction. An unmarked
cheese-global → ~/.cheeseblock is stale. Show the report. Ask the user for confirmation. Then use the explicit migration option. The installer never uses this option:
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.
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.
- yesterday Changed 50d75c0c87f5
- 4d ago Changed · +22 lines · -29 tokens per session f223ecbfdc7f
- 11d ago First seen · 47 lines · 133 tokens per session scan A cc7f57f7a9a2
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.
Other skills, from other repositories
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
cognitive-doc-design
Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.