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 skills add fmind/dot --skill dprintgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/dprint)<a href="https://agentmods.dev/skills/fmind/dot/dprint"><img src="https://agentmods.dev/badge/skills/fmind/dot/dprint/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/fmind/dot/dprint"><img src="https://agentmods.dev/badge/skills/fmind/dot/dprint.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00017 | $0.00720 |
| Opus 5.5 | $0.00007 | $0.00288 |
| Sonnet 5.5 | $0.00003 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
dprint 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 14d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dprint
The formatter for configuration and markup files (JSON, Markdown, TOML, YAML); dprint formats only, while Python formatting and linting live in ruff.
Configuration
dprint searches the current directory upward for dprint.json(c) or .dprint.json(c) and falls back to the global config (DPRINT_CONFIG_DIR) only when nothing is found. Global fallback can prompt before fmt; use a local, version-pinned configuration for non-interactive project gates.
- Copy (default): copy a known-good
dprint.jsoninto the project root; it is self-contained and version-pinned. The first run downloads uncached plugins; later runs use dprint's local cache. Bump plugin versions per repository. - Extends (DRY): set
"extends"to a single source of truth, a local path or a commit-pinned URL such as"https://raw.githubusercontent.com/fmind/dot/<commit>/dprint.json"; override rules or add plugins locally.
Commands
Repository tasks own the two gate commands; add and pin a plugin with dprint add <plugin>.
[tasks."format:dprint"]
description = "Format JSON, Markdown, TOML, YAML (dprint)"
run = "dprint fmt --allow-no-files" # mise appends the hook's {staged_files}; the flag keeps an empty list from exiting 14
[tasks."check:format"]
description = "Check config and markup formatting (dprint)"
run = "dprint check" # non-zero exit on drift
Gotchas
- Prefer
npm:plugin references:npm:@dprint/markdown@<version>overhttps://plugins.dprint.dev/...wasmURLs; both resolve, and the npm form makes the current version onenpm view <plugin> versionaway. - Plugin order is precedence: the
pluginsarray order decides which plugin claims a file; keep specialized plugins before generic ones. - Load plugins for embedded code: the Markdown plugin formats fenced JSON, TOML, and YAML only when those plugins are loaded too.
- Format staged, check the whole tree:
format:dprinttakes{staged_files}from the hook, which restages fixes;check:formatalways runs on the whole tree. Outside a hook,dprint fmt --stagedor--dirtyselects the staged or uncommitted files itself.
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.
- 14d ago Changed 87972c91390a
- 15d ago Changed · -6 lines · +5 tokens per session 5a305220b691
- 26d ago Changed 0534f648d4b3
- 29d ago Changed 131bfbf6f36d
- 1mo ago Changed · +1 lines · -21 tokens per session 66a088a75fcd
- 1mo ago Changed · +1 lines 60bc8a20444c
- 1mo ago Changed 9734c662bc14
- 1mo ago Changed · +1 lines abcb568f8a26
- 1mo ago First seen · 53 lines · 33 tokens per session scan A bbef5a3a2b97
dprint is a skill published in the GitHub repository fmind/dot (12 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 720 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
google-workspace-cli
Use gws across Workspace APIs with schema-first calls, profile isolation, bounded reads, and verified Drive, Docs, Sheets, Gmail, Calendar, or Chat writes.
handover
Write a self-contained follow-up prompt carrying this session's decisions, constraints, and verified findings into a fresh agent session. Use when handing unfinished work to a new context window.
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…
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…
dotfiles
Chezmoi dotfiles conventions and patterns. Use when modifying dotfiles, adding new managed files, working with chezmoi templates, or syncing agent skills and subagents through agentspec. Do NOT use for installing tools, running doctor, or updating a machine through the dotfiles CLI; use manage-machine.