Seatbelt
adamlinscott/claude-skillsSets 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 repo's existing Claude settings, instructions, MCP servers and CI before writing anything, and writes to gitignored local s...
At a glance
This skill is for Legal and helps you set up security policies for ai code execution, configure approval workflows for code changes, and establish spend limits and access controls.
/plugin marketplace add adamlinscott/claude-skills
/plugin install seatbelt
Setup, runtime and requirements describe adamlinscott/claude-skills, the repo this skill ships in.
ai-safetyaccess-controlcode-securitypolicyrisk-managementautomation
Also in adamlinscott/claude-skills
View the repoSurface and confirm the load-bearing assumptions behind a task before a long or expensive run — goal, root, what may be edited, what is off-...
Audits a repository's Claude context-injection setup — CLAUDE.md, CONTEXT.md, docs/, .claude/agents/, and the per-project memory directory....
BETA / under development. Mine the current project's Claude Code sessions for recurring corrections, then interrogate them — consolidate clu...
Fresh-context audit of a finished diff against the conversation's stated intent. A subagent with zero conversation history reviews the diff...
Run a settled implementation goal as a bounded autonomous build loop — lock the goal from the conversation and any docs written this session...
Audit Claude's per-user memory for this project and produce a report. Asks at the start whether the user wants a non-technical summary or a...
Halt a drifting agent and re-anchor it to codebase evidence for the current task, clearing speculative context without a full compaction. Us...
Alias for the seatbelt skill. Sets up the security foundation that lets you run Claude Code fast — auto mode, custom tools, minimal interrup...
Alias for the ttp skill. Shape user-facing output to be brief and direct — lead with the substance, keep the default answer short, and expan...
Shape user-facing output to be brief and direct — lead with the substance, keep the default answer short, and expand only when the user asks...
Other Legal skills
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use...
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's doc...
Meeting notes page — title bar with attendees, agenda checklist, decisions block, action items table with owners + dates, and a "next meetin...
An editorial-style poster — newsprint paper, dateline, oversized serif headline with a struck-through word and italic accent, a 2-column bod...
A standalone pricing page — header, plan tiers, feature comparison table, and an FAQ. Use when the brief asks for "pricing", "plans", "subsc...
Apple Human Interface Guidelines as 14 agent skills covering platforms, foundations, components, patterns, inputs, and technologies for iOS,...