Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/paulnsorensen/easy-cheese/pythongit clone --depth 1 https://github.com/paulnsorensen/easy-cheeseWhat 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 | $0.00678 | $0.00678 |
| Opus 5 | $0.00339 | $0.00339 |
| Sonnet 5 | $0.00136 | $0.00136 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
easy-cheese python.instructions.md 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python review checklist (skill validators + melt script tests)
Two Python surfaces live in this repo:
.github/scripts/— CI validators (validate_skills.py+test_validate_skills.py). These run onpython3from the GitHub Actions runner withpyyamlas the only third-party dependency. No virtualenv, nouv.tests/python/— pytest suite covering themeltskill's helper scripts (conflict_pick,conflict_summary,batch_resolve, etc.). Runs underpytestwith stdlib-style fixtures viaconftest.py.
Hard rules
- Dependencies are pinned in
validate.yml. The only allowed third-party imports arepyyaml(validators) andpytest(tests). Push back on PRs that pull inrequests,pydantic,pandas, etc. — every new dep means a bootstrap step in CI and another supply-chain edge. - Python 3.12 baseline. CI pins
python-version: "3.12". Don't reach for 3.13+ features without updatingvalidate.ymlfirst; don't write 3.8-compatible code "to be safe" either — the runner is fixed. - No filesystem writes from validators.
.github/scripts/files read and report; they never mutate the tree. A PR that adds autofix logic belongs in a separate skill or script, not invalidate_skills.py. - Exit-code propagation is load-bearing. Validators and pytest must
exit non-zero on failure, or CI silently passes.
except Exception:without re-raising orsys.exit(1)is a bug, not a style issue.
What to flag
- New top-level functions over 40 lines — decompose.
- Bare
except:orexcept Exception:that swallows errors in either surface. Validators must fail loud; tests must surface failures cleanly. - Tests in
tests/python/*.pyortest_validate_skills.pythat don't actually assert on observable behavior —assert Trueafter atry/exceptblock is not a test. - pytest tests that depend on filesystem state outside
tmp_pathor network access. Both make CI flaky. - Hard-coded paths that escape the repo root (e.g.
/Users/...,os.path.expanduser("~/Dev/...")). UsePath(__file__).resolve()or pytest'stmp_path/monkeypatch.chdir.
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 First seen · 56 lines · 678 tokens per session scan A 598116d85067
easy-cheese python.instructions.md is an instructions file published in the GitHub repository paulnsorensen/easy-cheese (18 stars, last pushed yesterday), licensed MIT. It adds 678 tokens to every session, about $0.0034 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 instructions, from other repositories
aider-desk AGENTS.md
Instructions for hotovo/aider-desk, covering agents.md, common commands, development, type checking and linting and formatting.
Meta_Kim CLAUDE.md
Instructions for KimYx0207/Meta_Kim, covering metakim for claude code, fast read, what this repository is, claude code's role and canonical vs runtime files.
crystal CLAUDE.md
Instructions for stravu/crystal, covering crystal - multi-session claude code manager, project overview, references, implementation status: ✅ complete and ✅ implemented features.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md — using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) — same for every tool and workflows.
AmbyKit CLAUDE.md
Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.
sugar AGENTS.md
AGENTS.md instructions for roboticforce/sugar, covering sugar - agents.md, git branching rules (strict), always create branches from develop, after work is complete and then create pr targeting develop.