How do I install the Press1 Check skill?

Run npx skillmds@latest add christophecapel/press1-check in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Press1 Check safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Press1 Check?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Press1 Check free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Press1 Check?

christophecapel (@christophecapel) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Press1 Check by christophecapel — Agent Skill

Name: Press1 Check
Author: christophecapel

Press1 Check

Audit which Bash commands required manual approval ("press 1") in Claude Code sessions. Use when the user says "press1-check", "press 1 check", "permission audit", or wants to review which commands need allow-listing.

christophecapel 7c6534e 3 files · 23.2 KB Updated Sep 17, 2026

File contents

/press1-check -- Permission Audit

Audit which Bash commands triggered manual approval prompts in Claude Code sessions.

How it runs

Two paths:

Manual: type /press1-check to force a re-audit. Default mode is since the last run (state-tracked at ~/.claude/state/press1-check.json), so the typical run only surfaces new ground.
Auto (optional): the script supports --auto-stop-hook mode designed to be wired as a Claude Code Stop hook. State at ~/.claude/state/press1-check.json. 6-hour cooldown bounds compute. When LOW-risk additions are found, a one-shot summary at ~/.claude/hooks-state/press1-check-pending.json surfaces in the next session-start priority snapshot. See README for setup.

Usage

/press1-check -- since the last run (default, state-tracked)
/press1-check --days N -- last N days across all project dirs
/press1-check --latest-session -- only the single most recent session
/press1-check --all-recent -- all sessions from the last 24h
/press1-check --since YYYY-MM-DD -- all sessions since a date
/press1-check <session-id> -- specific session

Steps

Run: python3 audit-permissions.py with any arguments the user provided. Default audits since ~/.claude/state/press1-check.json#last_run_ts (bootstraps to last 3 days when state is missing, e.g. on a new machine).
Display the output to the user exactly as printed (it includes color-coded risk levels).
If LOW-risk suggestions appear, add them to ~/.claude/settings.json (read-only commands are safe). Skip env-var-prefix suggestions like Bash(WT=*) -- they don't generalize because the actual command follows the assignment.
Do NOT auto-add MEDIUM or HIGH risk commands without explicit approval.
After editing ~/.claude/settings.json, re-run the audit and report before/after counts so the user can see the coverage delta.
Each successful interactive run updates the state file -- the next run is automatically scoped to "since now."

---name: press1-checkdescription: Audit which Bash commands required manual approval ("press 1") in Claude Code sessions. Use when the user says "press1-check", "press 1 check", "permission audit", or wants to review which commands need allow-listing.---# /press1-check -- Permission AuditAudit which Bash commands triggered manual approval prompts in Claude Code sessions.## How it runsTwo paths:- **Manual:** type `/press1-check` to force a re-audit. Default mode is *since the last run* (state-tracked at `~/.claude/state/press1-check.json`), so the typical run only surfaces new ground.- **Auto (optional):** the script supports `--auto-stop-hook` mode designed to be wired as a Claude Code `Stop` hook. State at `~/.claude/state/press1-check.json`. 6-hour cooldown bounds compute. When LOW-risk additions are found, a one-shot summary at `~/.claude/hooks-state/press1-check-pending.json` surfaces in the next session-start priority snapshot. See README for setup.## Usage- `/press1-check` -- since the last run (default, state-tracked)- `/press1-check --days N` -- last N days across all project dirs- `/press1-check --latest-session` -- only the single most recent session- `/press1-check --all-recent` -- all sessions from the last 24h- `/press1-check --since YYYY-MM-DD` -- all sessions since a date- `/press1-check <session-id>` -- specific session## Steps1. Run: `python3 audit-permissions.py` with any arguments the user provided. Default audits since `~/.claude/state/press1-check.json#last_run_ts` (bootstraps to last 3 days when state is missing, e.g. on a new machine).2. Display the output to the user exactly as printed (it includes color-coded risk levels).3. If LOW-risk suggestions appear, add them to `~/.claude/settings.json` (read-only commands are safe). Skip env-var-prefix suggestions like `Bash(WT=*)` -- they don't generalize because the actual command follows the assignment.4. Do NOT auto-add MEDIUM or HIGH risk commands without explicit approval.5. After editing `~/.claude/settings.json`, re-run the audit and report before/after counts so the user can see the coverage delta.6. Each successful interactive run updates the state file -- the next run is automatically scoped to "since now."

Frequently asked questions