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

Report

ASecurity

Render the rashomon report: declarations, executions, per-transcript accounting and coverage for recorded Claude Code sessions. Use when the user says "rashomon report", "show what the session did", "session recording report", or asks what rashomon captured.

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

Works with

claude codeterminal

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Report?

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

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

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

Files
SKILL.md
---
name: report
description: 'Render the rashomon report: declarations, executions, per-transcript accounting and coverage for recorded Claude Code sessions. Use when the user says "rashomon report", "show what the session did", "session recording report", or asks what rashomon captured.'
---

Render what the recorder captured. This command reads; it writes nothing and
creates no store.

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

2. Pick flags from what the user asked for, passing through any they named:
   - default: `$RASHOMON report` — text for a terminal
   - a specific session: `--session <id>`
   - machine-readable: `--json`
   - to share outside the team: `--redact` (hostnames become keyed digests
     and the agent's prose summary is dropped)
   - which prompt produced which calls: `--chain` (lists each call under its
     prompt, with the hosts the call named; JSON always carries this)

3. Show the output. If it is long, show the coverage block and the
   per-transcript accounting in full and summarize the id lists; never
   summarize a number into a different claim. When reading it for the user,
   keep the report's own distinctions:
   - `without execution` is not a list of denials — it holds denied, failed,
     and unrecorded calls together, each with its permission mode.
   - `unknown` and `not read` are never `0`.
   - `coverage: unverified` with `probe_absent` is expected for any session
     the recorder joined mid-way (including the session that enabled this
     plugin).

If the report says "no sessions recorded", say so and point the user at
`/rashomon:watch` to start recording — do not run `watch` yourself from here.

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 →