seatbelt SKILL.md skillB

seatbelt from adamlinscott/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add adamlinscott/claude-skills/seatbelt@git:20260911.623fe4a

Pins git:20260911.623fe4a in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
adamlinscott/claude-skills
Path
skills/seatbelt/SKILL.md
Versions recorded
3
Latest version
git:20260911.623fe4a, committed Sep 11, 2026
First version recorded
Jul 27, 2026
Size
8,321 bytes
Repository stars
4
License
MIT

[Adam''s Skills] Sets up the security foundation that lets you run Claude Code fast — auto mode, custom tools, minimal interruptions — without it doing something irreversible you never asked for. Two modes. Developer, a permissive default plus a thin deny-only brake on the genuinely irreversible. Vibe, deny-by-default for people who don''t know git, so code changes flow freely while merges, force-pushes, deploys, secret reads and spend are blocked at the Claude layer. Grounds itself in the…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Seatbelt

A seatbelt doesn't limit how fast you drive. It's what lets you drive fast at all.

This skill writes a per-person permission policy for the current repo so Claude can be given
more autonomy, not less. It is the collection's only **mutating** skill — everything else here
is read-only. For a read-only report on this repo's AI setup, use `/context-audit` instead;
this skill deliberately has no dry-run mode, because that would just be `/context-audit` again.

**What it honestly does:** stops Claude over-reaching. **What it does not do:** stop a person
who dismantles their own setup. Say this to the user; never let them believe otherwise.

**Explicit invocation only** (`disable-model-invocation: true`). Never offer or auto-run this
because a user sounded worried, said Claude broke something, or challenged a change. A developer
with their own permission setup would find an uninvited rewrite of it worse than the problem
they were complaining about. It runs when someone types `/seatbelt`, and not otherwise.

## Quick start

```
/seatbelt              # asks which mode, then sets up
/seatbelt --developer  # skip the question
/seatbelt --vibe       # skip the question
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add adamlinscott/claude-skills/seatbelt@sha256:c0fb9f9e6939f979

The line at the top of this page pins the label git:20260911.623fe4a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_6clqmqg2bewjbylp.svg)](https://markdownregistry.com/a/art_6clqmqg2bewjbylp)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Jul 27, 2026 and Sep 11, 2026, about one every 23 days.

versioncommittedcommitsizeaudit
git:20260911.623fe4a latest2026-09-11 623fe4a 8,321 BB view · diff
git:20260910.7e7f4622026-09-10 7e7f462 8,318 BB view · diff
git:20260727.05743f52026-07-27 05743f5 8,300 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No instruction to read or print local credentials (matched: Read(path)`, relative-anchored (`Read(./.env)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8321 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

adamlinscott/claude-skills · 4 stars · license MIT · pushed 2026-10-30 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_6clqmqg2bewjbylp
GET https://markdownregistry.com/api/v1/resolve?ref=adamlinscott/claude-skills/seatbelt
GET https://markdownregistry.com/api/v1/blob/c0fb9f9e6939f9792834194fa33d269f527f7cf21407401743c7ec48d8047ca7

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from adamlinscott/claude-skills

are-we-done SKILL.md skill
adamlinscott/claude-skills · skills/are-we-done/SKILL.md · [Adam''s Skills] Deterministic close-out gate for a session or work tree. Sweeps a fixed set of sources — the todo…
git:20261030.7081899 · audit A · 4 stars
assumption-inventory SKILL.md skill
adamlinscott/claude-skills · skills/assumption-inventory/SKILL.md · [Adam''s Skills] DEPRECATED — superseded by /build-it. Do not use for new work. Surfaced the load-bearing assumptions…
git:20260911.623fe4a · audit A · 4 stars
brief-me SKILL.md skill
adamlinscott/claude-skills · skills/brief-me/SKILL.md · [Adam''s Skills] DEPRECATED — superseded by /where-are-we. Do not use for new work. Printed a plain-English re-entry…
git:20261026.c0a4905 · audit A · 4 stars
build-it SKILL.md skill
adamlinscott/claude-skills · skills/build-it/SKILL.md · [Adam''s Skills] Build a piece of work, from wherever it is written down — a ticket number or URL, a plan or spec file…
git:20261008.a87265d · audit A · 4 stars
check-skill-updates SKILL.md skill
adamlinscott/claude-skills · skills/check-skill-updates/SKILL.md · [Adam''s Skills] Check whether the installed copy of this skills collection is behind its remote, and offer to update…
git:20261026.c0a4905 · audit A · 4 stars
context-audit SKILL.md skill
adamlinscott/claude-skills · skills/context-audit/SKILL.md · [Adam''s Skills] Audits a repository''s Claude context-injection setup — CLAUDE.md, CONTEXT.md, docs/, .claude/agents/…
git:20261008.fda8754 · audit A · 4 stars
debrief SKILL.md skill
adamlinscott/claude-skills · skills/debrief/SKILL.md · [Adam''s Skills] BETA / under development. Mine the current project''s Claude Code sessions for recurring corrections…
git:20260911.623fe4a · audit A · 4 stars
fresh-eyes SKILL.md skill
adamlinscott/claude-skills · skills/fresh-eyes/SKILL.md · [Adam''s Skills] Fresh-context audit of a finished diff against the conversation''s stated intent. A subagent with zero…
git:20261008.fda8754 · audit A · 4 stars
goal-workflow SKILL.md skill
adamlinscott/claude-skills · skills/goal-workflow/SKILL.md · [Adam''s Skills] DEPRECATED — superseded by /build-it. Do not use for new work. Ran a settled goal as a bounded…
git:20260911.623fe4a · audit A · 4 stars
memory-audit SKILL.md skill
adamlinscott/claude-skills · skills/memory-audit/SKILL.md · [Adam''s Skills] Audit Claude''s per-user memory for this project and produce a report. Asks at the start whether the…
git:20261008.fda8754 · audit A · 4 stars
raise-issue SKILL.md skill
adamlinscott/claude-skills · skills/raise-issue/SKILL.md · [Adam''s Skills] Turns "this is broken" into a well-formed issue in the team''s tracker, written in the codebase''s own…
git:20261008.fda8754 · audit A · 4 stars
reground SKILL.md skill
adamlinscott/claude-skills · skills/reground/SKILL.md · [Adam''s Skills] Halt a drifting agent and re-anchor it to codebase evidence for the current task, clearing speculative…
git:20260911.623fe4a · audit A · 4 stars

Every file in adamlinscott/claude-skills

Browse by kind, by grade B, or by owner.