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/hard-cheeseWrote 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/hard-cheese)<a href="https://agentmods.dev/skills/paulnsorensen/easy-cheese/hard-cheese"><img src="https://agentmods.dev/badge/skills/paulnsorensen/easy-cheese/hard-cheese/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/hard-cheese"><img src="https://agentmods.dev/badge/skills/paulnsorensen/easy-cheese/hard-cheese.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00067 | $0.02918 |
| Opus 5 | $0.00034 | $0.01459 |
| Sonnet 5 | $0.00013 | $0.00584 |
| Haiku 4.5 | $0.00007 | $0.00292 |
Grade A, and why
hard-cheese 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 5d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hard-cheese
The gate reduces epistemic debt. This debt exists when code passes checks, but the author cannot explain it.
Inputs
/hard-cheese [<slug>] [--socratic-cap N=3] [--passing-score N=3] [--no-judge]
Arguments:
<slug>identifies the artifact at.cheese/hard-cheese/<slug>.md. This argument is optional. Without it, use the short SHA ofHEAD. An explicit slug overrides the SHA.--socratic-cap Nsets the maximum number of retries. The gate then marks the artifactFAILEDand returns a non-zero status. The default is3. Vibecheck has no limit, but easy-cheese prevents infinite loops.--passing-score Nsets the minimum SOLO score for PASS. Use a value from1through5. The default is3. The gate treats a previous PASS below this value as stale.--no-judgeenables log-only mode. Record the user's explanation withstatus: LOGGED. Do not start the judge sub-agent. This mode is the easy-cheese equivalent of the optional JSONL telemetry mode in vibecheck. It retains more content. See## Divergence from the paper.
Invocation modes
| Mode | How the gate runs | Where the gate sits |
|---|---|---|
| standalone | The user runs /hard-cheese <slug> before a pull request. |
Outside the pipeline. No upstream skill is required. |
| propagated | /plate --hard runs /hard-cheese <slug> after the final writes and before publication. |
At the verified-artifacts to share-for-review boundary. |
--hard passes through /cheese → /mold → /cook → /press → /age → /cure → /plate. Only /plate runs /hard-cheese.
See ../cheese/references/harness-portability.md for portability requirements. It covers helper resolution, sub-agent dispatch, GitHub operations, and handoff transitions.
Use the bundle or repository helper first. Use ${CLAUDE_SKILL_DIR} only as an optional host fallback.
The handoff blocks define the portable contract because slash commands are host renderings, not the control model.
What ships with it
4 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.
- 5d ago Changed · +25 lines · -69 tokens per session a0dbb9b30db5
- 11d ago First seen · 206 lines · 136 tokens per session scan A 558a14c49344
hard-cheese is a skill published in the GitHub repository paulnsorensen/easy-cheese (18 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 2,918 once invoked, about $0.0003 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.