Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Watch

ASecurity

Start recording what this Claude Code session asks to run. Use when the user says "rashomon", "start rashomon", "claude rashomon", "watch this session", "record my session", asks to turn the recorder on, or wants an easier way to launch recorded sessions. For reports use /rashomon:report; to stop use /rashomon:stop; for install state use /rashomon:status.

8 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agents

Works with

claude codecli

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add altrace-dev-role/rashomon --skill watch --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Watch?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Watch
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/altrace-dev-role-watch/badge)](https://www.skillsdirectory.com/skills/altrace-dev-role-watch)

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: watch
description: 'Start recording what this Claude Code session asks to run. Use when the user says "rashomon", "start rashomon", "claude rashomon", "watch this session", "record my session", asks to turn the recorder on, or wants an easier way to launch recorded sessions. For reports use /rashomon:report; to stop use /rashomon:stop; for install state use /rashomon:status.'
---

This plugin ships disabled: enabling it is the only thing that starts
recording, and installing it (adding the marketplace, or having it enabled by
policy) does not, by itself.

1. The binary is `${CLAUDE_PLUGIN_ROOT}/bin/rashomon` — it ships with this
   plugin, so there is nothing to resolve and nothing to build. Set
   `$RASHOMON` to that path.

2. If this skill is reachable at all, the plugin is enabled, and its eight
   hook entries (PreToolUse, PostToolUse, PostToolUseFailure, SessionStart,
   SessionEnd, Stop, StopFailure, UserPromptSubmit) are already configured — enabling the plugin is what installs
   them, the same way `watch` installs the settings-file form. There is
   normally nothing further to run. Confirm with `$RASHOMON status`, which
   reports this plugin's entries and a settings install separately: if both
   read live, relay the `overlap` line and its `rashomon detach` resolution.

3. Do NOT run `$RASHOMON watch` from here as a matter of course: it writes
   the settings-file form of these same eight entries, and it refuses when
   this plugin already provides them, naming the plugin and pointing at
   disabling it — because installing both would record every tool call
   twice, and nothing at the hook layer can undo that once both origins are
   live. If a user specifically wants the settings-file form instead of this
   plugin (for example, to keep recording after disabling the plugin), point
   them at `$RASHOMON watch` directly rather than running it for them, so
   they see the refusal and the reason if the plugin is still enabled.

4. Tell the user, briefly, and say the SCOPE first — it is the part they are
   actually agreeing to:
   - Recording is USER-WIDE AND OPEN-ENDED, not this session and not this
     project. Once enabled, every session from now on is recorded —
     including unrelated repositories and client work — until the plugin is
     disabled. Someone who is under an agreement not to instrument a
     particular codebase needs to know that before saying yes, not after.
   - Recording covers tool calls from this point on. A session the recorder
     joined mid-way reports its coverage as `unverified` (reason
     `probe_absent`) — that is honest accounting, not a failure. Sessions
     started after this plugin was enabled are eligible for verified
     coverage, because the probe is in place from their first moment; the
     report is the proof.
   - `/rashomon:report` renders what was recorded; `/rashomon:stop` removes
     a settings install (not this plugin's own entries — disable the plugin
     for that); `/rashomon:forget` erases records.

Do not edit `~/.claude/settings.json` by hand, and do not run `watch` or
`detach` as a substitute for enabling or disabling this plugin — the two
origins are independent, and mixing them up is exactly what the `overlap`
line in `status` exists to catch.

Attribution

altrace-dev-rolealtrace-dev-role
View sourceMore from altrace-dev-role →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

695601 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →