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/dotfiles --skill misegit clone --depth 1 https://github.com/fmind/dotfilesWrote 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/dotfiles/mise)<a href="https://agentmods.dev/skills/fmind/dotfiles/mise"><img src="https://agentmods.dev/badge/skills/fmind/dotfiles/mise/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/dotfiles/mise"><img src="https://agentmods.dev/badge/skills/fmind/dotfiles/mise.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 | $0.00027 | $0.01925 |
| Opus 5.5 | $0.00011 | $0.00770 |
| Sonnet 5.5 | $0.00005 | $0.00385 |
| Haiku 4.5 | $0.00003 | $0.00193 |
Grade A, and why
mise 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 1mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mise Standard
Canonical setup for mise as the per-project task runner and tool-version manager. One mise.toml defines the task vocabulary that git hooks and CI reuse, and pins the toolchain for reproducibility. Mise is the single source of truth for what every check does; lefthook and github-actions only decide when to run them.
Task Vocabulary
Every project exposes the same core tasks (with short aliases) so agents, hooks, and CI stay portable. In interactive shells, mr <task> is the standard command-line alias used for mise run <task>:
| Task | Alias | Purpose |
|---|---|---|
install |
i |
Sync dependencies and install git hooks (lefthook install). |
format |
f |
Format all sources (fans out to format:*). |
check |
c |
All static checks in parallel (fans out to check:*). |
test |
t |
Run the test suite. |
build |
b |
Compile or package artifacts (fans out to build:*). |
watch |
w |
Run the app with live reload (web). |
Language stacks ship concrete mise.toml files — see go-stack and python-stack.
Naming: generic vs specific
Split a task into <task>:<x> subtasks when you want to run one piece on its own. Each family keys <x> off a different noun, because each answers a different question:
format:<input>— key off the source you format (the file family):format:go,format:python,format:templ,format:shell. Fall back to the tool name only when the domain has no single language noun:format:dprint(JSON/Markdown/TOML/YAML).check:<concern>— key off the property verified, tool-agnostic and identical across languages somise run check:lintmeans the same everywhere:check:format,check:lint,check:types,check:vuln,check:leaks(secret/credential scan, e.g.gitleaks),check:scan(IaC/config misconfig, e.g.trivy config),check:actions(GitHub Actions workflow lint + audit:actionlint+zizmor— see github-actions). Use one name per concern — dependency-vulnerability scanning is alwayscheck:vuln(nevercheck:audit), whether it runsgovulncheckorpip-audit; secret scanning is alwayscheck:leaks; misconfiguration scanning ischeck:scan, distinct fromcheck:vuln.build:<output>— key off the artifact produced:build:go(binary),build:css,build:html(generated Templ→Go).
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.
- 1mo ago First seen · 81 lines · 27 tokens per session scan A fe78a023c33c
mise is a skill published in the GitHub repository fmind/dotfiles (4 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 1,925 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 2026-08-31.
Other skills, from other repositories
full-review
Full review: read every repo area, apply verified fixes, and prove all checks pass.
airflow
Develop and test Airflow DAGs with the Astronomer astro CLI.
smoke
Smoke-test every repo task and CLI command; warnings count as failures.
mise
Manage mise tool pins, lockfiles, environments, and tasks shared by hooks and CI.
quality-assurance
Plan and run QA test campaigns over user journeys, failure modes, and release risks.
playwright
Automate browsers and E2E tests with Python Playwright: screenshots, traces.