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 skills/fmind/dotfiles/cli-contractsnpx skills add fmind/dotfiles --skill cli-contractsgit clone --depth 1 https://github.com/fmind/dotfilesWhat 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 | $0.00034 | $0.00594 |
| Opus 5 | $0.00017 | $0.00297 |
| Sonnet 5 | $0.00007 | $0.00119 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
cli-contracts 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineer CLI Contracts
Define a command-line interface as a stable human and machine contract before implementing it. Pair with go-stack or python-stack for language-specific code and systematic-debugging for unknown failures.
Contract
- Name the jobs: Give each command one purpose, a predictable noun/verb hierarchy, and aliases only when they cannot trigger a different class of action.
- Specify inputs: Define positional arguments, flags, environment variables, config precedence, defaults, validation, mutual exclusions, and behavior without a TTY.
- Separate streams: Send requested data to stdout and diagnostics or progress to stderr. Keep
--jsonmachine-readable, schema-stable, and free of decoration. - Define outcomes: Map success, usage errors, authentication failures, remote failures, partial results, and cancellation to documented exit codes. Never convert an error into an empty success.
- Make help executable: Ensure root and subcommand help, examples, deprecations, and shell completions are generated from the same command definition.
- Protect sensitive context: Render safe command and argument context for actionable errors, but never include collected values, tokens, provider response bodies, or unredacted stderr.
- Handle process behavior: Respect signals, cancellation, timeouts, piping, broken pipes, and cleanup. Destructive commands need a confirmation mechanism or explicit non-interactive opt-in, while agent execution still requires separate target-scoped user authority; a
--yesflag is never authority. - Preserve compatibility deliberately: Treat command names, flags, JSON fields, exit codes, and stdout text consumed by scripts as public API. Prefer deprecation and migration guidance over silent changes.
Verification
- Write contract tests for help, parsing, validation, streams, exit codes, JSON schema, cancellation, and representative success and failure paths.
- Exercise the installed binary from a clean shell, including piped and non-TTY use; do not rely only on direct function tests.
- Run the focused tests, completion generation, documentation checks, and the repository's full gate.
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 · 36 lines · 34 tokens per session scan A 4de8c8762459
cli-contracts is a skill published in the GitHub repository fmind/dotfiles (4 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 594 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
aiq-research
Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.
obsidian-bases
Obsidian Bases database feature for YAML-based interactive note views. Use when creating .base files, writing filter queries, building formulas, configuring table/card views, or working with Obsidian properties and frontmatter databases.
telegram
Send notifications, interactive questions, or multiple-choice polls to the user via Telegram. Use when the user asks to be notified ("ping me", "notify me on Telegram", "ask me when..."), when a long-running task finishes and the user is likely away, when an irreversible action needs out-of-band confirmation, or when…
chezmoi-expert
Comprehensive chezmoi dotfiles management expertise including templates, cross-platform configuration, file naming conventions, and troubleshooting. Covers source directory management, reproducible environment setup, and chezmoi templating with Go templates. Use when user mentions chezmoi, dotfiles, cross-platform…