AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Cli Command Surface Audit

skill-ychampion-cskill-agents-cli-command-surface-audit · by ychampion

Audit a command surface end to end so registration, discoverability, permissions, and execution all line up before shipping.

No reviews yet
0 installs
14 views
0.0% view→install

Install

$ agentstack add skill-ychampion-cskill-agents-cli-command-surface-audit

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-ychampion-cskill-agents-cli-command-surface-audit)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
4mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Cli Command Surface Audit? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

SKILL: CLI Command Surface Audit

Domain: command-surfaces Trigger: Use when adding, migrating, or debugging commands or slash-command skills in a coding CLI that builds its surface from multiple registries. Source Pattern: Distilled from reviewed command-surface, help-menu, and execution-path consistency implementations.

Core Method

Audit the entire command surface, not just the handler. Confirm where the command is registered, how it is filtered, how it is described to users, and which runtime modes can actually execute it. Check help output, skill pickers, slash-command lookup, remote-safe filtering, and user-invocable flags against the real execution path. A command is only complete when the same name, description, permissions, and invocation contract stay aligned across all of those layers.

Key Rules

  • Verify both visibility and executability; a command that only exists in code is still broken.
  • Audit registration order and source precedence before debugging the handler itself.
  • Check feature gates, permission filters, and remote-safe filters separately because each can hide the command for a different reason.
  • Keep the displayed description and argument hint consistent with the actual invocation contract.
  • Exercise at least one real end-user invocation path after wiring the command in.

Example Application

If you add a new slash command to a coding CLI, trace it from registry construction to help output to command execution. Confirm it survives the feature gate, appears in the skill list with the right summary, remains visible in the modes that should expose it, and actually dispatches through the same runtime path the user will hit.

Anti-Patterns (What NOT to do)

  • Don’t stop after the handler compiles; the command may still be absent from the visible surface.
  • Don’t assume a help entry means the command is executable under the current permission or runtime mode.
  • Don’t let multiple registries describe the same command differently.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.