Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Inspect

ASecurity

Read the operator's machine and troth's own state through the proxy — burners, unified log, proxy log, plan window, a ChatGPT-lane probe — without asking the operator to run anything.

10 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agentsshellbashapidatabase

Works with

api

Security Analysis

A100/100

Scanned 9/20/2026

$npx -y skills add xgre1/troth --skill inspect --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Inspect?

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

Security grade badge for Inspect
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/xgre1-inspect/badge)](https://www.skillsdirectory.com/skills/xgre1-inspect)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: inspect
description: Read the operator's machine and troth's own state through the proxy — burners, unified log, proxy log, plan window, a ChatGPT-lane probe — without asking the operator to run anything.
allowed-tools: ["Bash"]
kind: deterministic
---

The partner's shell runs inside a ground wall. Two things no wall can carry:
setuid tools (`ps`, `top`) refuse to exec under a seatbelt, and `log show`
refuses to run while sandboxed. `~/.troth` stays dark by design (keys, the
token store, the substrate database). The proxy runs OUTSIDE the walls under
its service manager and answers these questions on your behalf, read-only,
localhost-only, redacted. Use these roads; never ask the operator to run
`ps`, `top`, `log show` or an engine probe for you.

All at `http://localhost:8000` (or the port in `TROTH_PROXY_URL`):

- **What is burning the machine** — `GET /api/system/load`: troth's own
  processes (role, pid, memory, CPU seconds, port, idle countdown) and
  `top.by_cpu` / `top.by_rss`, the machine-wide leaders by CPU time consumed
  and by resident memory, command name only. CPU time consumed identifies a
  burner; %CPU is a lifetime average and lies.
- **What the system logged** — `GET /api/system/log?last=5m&predicate=process == "troth-app"&limit=200`:
  a bounded `log show`. `last` is a number and a unit (`30s`, `5m`, `2h`, at
  most a day); the predicate is plain `log` syntax; macOS only.
- **What the proxy logged** — `GET /api/logs?grep=PAYLOAD&limit=40` over a
  2000-line buffer (`since=<ms>` for the newer part). `PAYLOAD BREAKDOWN` and
  `PAYLOAD AFTER INJECT` lines measure a lane's request shape.
- **Does the ChatGPT lane answer** — `GET /api/providers/codex/probe?model=gpt-5.6-sol`:
  one word through the proxy's own token. Answers `ok` and the model that
  served, or the status, the reason and `resets_in_seconds` on a plan limit.
  The token never leaves the proxy.
- **Usage and the plan window** — `GET /api/stats`
  (`persistent_provider_usage.recent_5h.by_model`), `GET /api/usage/plan-window`.
- **Health** — `GET /api/health/vitals`, `GET /api/doctor`,
  `GET /api/providers/codex/status`, `GET /api/config` (redacted).

Writing a handoff file for the operator: run from the operator's own folder
(`cwd: ~/Desktop` or a project). The tree holding the substrate
(`/Users/<operator>`) is scratch-only ground.

If the proxy is offline (curl fails), say so plainly; do not invent numbers.

Attribution

xgre1xgre1
View sourceSee grades on GitHubMore from xgre1 →
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

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 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', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 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.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, 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.

741 votes
View all in ai-agents →