Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/radumarias/xorio-claude-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/radumarias/xorio-claude-plugin/check-deps)<a href="https://agentmods.dev/commands/radumarias/xorio-claude-plugin/check-deps"><img src="https://agentmods.dev/badge/commands/radumarias/xorio-claude-plugin/check-deps/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/radumarias/xorio-claude-plugin/check-deps"><img src="https://agentmods.dev/badge/commands/radumarias/xorio-claude-plugin/check-deps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00010 | $0.01088 |
| Opus 5 | $0.00005 | $0.00544 |
| Sonnet 5 | $0.00002 | $0.00218 |
| Haiku 4.5 | $0.00001 | $0.00109 |
Grade B, and why
check-deps scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Read `~/.claude/settings.json` and check the `enabledPlugins` object for these keys: How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Check
Verify that all external plugins and MCP servers required by the xorio plugin are available.
Check Plugins
Read ~/.claude/settings.json and check the enabledPlugins object for these keys:
Required (workflows break without these):
pr-review-toolkit— used by/xorio:polishand/xorio:reviewralph-wiggum— used by/xorio:polish --autosecurity-guidance— automatic security hooks on file edits, used by polish/review workflows
Recommended (enhance workflows but not strictly required):
feature-dev— guided feature developmentfrontend-design— UI component developmentsuperpowers— general workflow enhancement (plan mode, brainstorming, TDD, code-reviewer)commit-commands— git commit/push/PR workflows (complementsxorio:commit-message)claude-md-management— CLAUDE.md maintenance (used at end of polish/review workflows)rust-analyzer-lsp— compile-time diagnostics for Rust projects
For each plugin, check if a key containing that name exists in enabledPlugins and is set to true.
Check MCP Servers
Use ToolSearch to check if the following MCP tools are discoverable:
Required:
context7— documentation lookup. Search for tool prefixmcp__plugin_context7_context7__ast-grep— structural code search. Search for tool prefixmcp__ast-grep__serena— symbol navigation. Search for tool prefixmcp__plugin_serena_serena__
Recommended:
memory— knowledge graph for cross-session context. Search for tool prefixmcp__memory__claude-in-chrome— browser testing/debugging for web projects. Search for tool prefixmcp__claude-in-chrome__
Report
Present results as a table:
## xorio dependency check
| Dependency | Type | Status | Used by |
|---|---|---|---|
| pr-review-toolkit | plugin | OK/MISSING | polish, review |
| ralph-wiggum | plugin | OK/MISSING | polish --auto |
| security-guidance | plugin | OK/MISSING | polish, review, cleanup-code |
| feature-dev | plugin | OK/MISSING (optional) | build workflow |
| frontend-design | plugin | OK/MISSING (optional) | build workflow |
| superpowers | plugin | OK/MISSING (optional) | polish, review (code-reviewer) |
| commit-commands | plugin | OK/MISSING (optional) | git workflows |
| claude-md-management | plugin | OK/MISSING (optional) | polish, review (CLAUDE.md updates) |
| rust-analyzer-lsp | plugin | OK/MISSING (optional) | Rust projects |
| context7 | MCP | OK/MISSING | cleanup-code, tests |
| ast-grep | MCP | OK/MISSING | cleanup-code, analysis |
| serena | MCP | OK/MISSING | cleanup-code, analysis |
| memory | MCP | OK/MISSING (optional) | cross-session knowledge |
| claude-in-chrome | MCP | OK/MISSING (optional) | web project testing |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 112 lines · 10 tokens per session scan B 28a4d72f304c
check-deps is a command published in the GitHub repository radumarias/xorio-claude-plugin (3 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 1,088 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.