Borrowing it
Nothing to install: this file belongs to frostyard/snosi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/frostyard/snosi/main/.github/prompts/README.mdgit clone --depth 1 https://github.com/frostyard/snosiWrote 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/commands/frostyard/snosi/readme)<a href="https://agentmods.dev/commands/frostyard/snosi/readme"><img src="https://agentmods.dev/badge/commands/frostyard/snosi/readme.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 | $0.00000 | $0.00303 |
| Opus 5 | $0.00000 | $0.00151 |
| Sonnet 5 | $0.00000 | $0.00061 |
| Haiku 4.5 | $0.00000 | $0.00030 |
Grade A, and why
README 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.
What it actually says
Prompts catalog
Reusable prompts for AI coding agents working in this repository.
Each file is a task-scoped prompt: paste it (or reference it) at the start of a
session, then replace the <...> placeholders with the specifics of your task.
Every prompt assumes the agent has first read CLAUDE.md and docs/design/overview.md,
which hold the architecture, contracts, and operational constraints that most
mistakes in this repository come from ignoring.
| Prompt | Use it for |
|---|---|
add-sysext.md |
Adding or changing a system extension under mkosi.images/ |
native-ab-change.md |
Touching the native A/B profiles, channels, or update path |
update-docs.md |
Bringing CLAUDE.md, README.md, and docs/ back in sync with code |
triage-ci-failure.md |
Investigating a failed workflow run |
Conventions
- Prompts describe how to work here, not project status; keep status in
CLAUDE.mdanddocs/. - Keep each prompt self-contained and under roughly one screen.
- When a contract changes (for example
docs/native-ab-contracts.md), update the prompt that points at it in the same pull request.
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 · 25 lines · 0 tokens per session scan A 112d7a870b90
README is a command published in the GitHub repository frostyard/snosi (24 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 303 tokens. 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 2026-09-06.
Other commands, from other repositories
domains
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
access
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
check-release-health
Summarize the CI health of an OpenShift release using live data from the openshift-ci-mcp server.
analyst
Use when performing local analyst review before pushing PR changes. Assesses code quality, impact analysis, and maintainability.
release
Standalone SDK release command for the BUILD repo. Not a workspace phase — runs independently after any number of implement/redteam cycles. Handles PyPI publishing, documentation deployment, and CI management for the kailash Python SDK and its framework packages.
cf-scaffold-project
Scaffold a Cloudflare project — Worker, Pages, or Worker+D1+R2 starter — with Wrangler config, Terraform skeleton, and GitHub Actions deploy using scoped API tokens.