An interactive guide to workflows for common software tasks, such as testing, code review, feature building, debugging, and dependency checks.

Use it to inspect project context, get a recommendation, or start a named workflow directly.

It helps you choose a suitable workflow based on your project instead of needing to know every available command.

guide — Command for coding agents by radumarias: An interactive guide to workflows for common software tasks…

Install

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.

agentmods

npx agentmods add commands/radumarias/xorio-claude-plugin/guide

Clone the repo

git clone --depth 1 https://github.com/radumarias/xorio-claude-plugin

Or install xorio, the plugin that ships this one along with the rest of its 10 skills, 10 commands, 4 agents, 2 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/radumarias/xorio-claude-plugin/guide.svg)](https://agentmods.dev/commands/radumarias/xorio-claude-plugin/guide)

Your own site

<a href="https://agentmods.dev/commands/radumarias/xorio-claude-plugin/guide"><img src="https://agentmods.dev/badge/commands/radumarias/xorio-claude-plugin/guide.svg" alt="Measured on agentmods" height="20"></a>

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,866 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00014	$0.03866
Opus 5	$0.00007	$0.01933
Sonnet 5	$0.00003	$0.00773
Haiku 4.5	$0.00001	$0.00387

Measured 4d ago against content hash af53f38b814b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

guide scanned grade A with 0 findings 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 4d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/guide.md · 362 lines

How it starts

The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guide Command

Interactive onboarding — detect project context, show available workflows, recommend a starting point, and launch chosen workflow.

Argument Parsing

Parse $ARGUMENTS. If a workflow name is provided, set DIRECT_MODE to that workflow name and skip Steps 2-3.

Valid workflow names (also accept common aliases):

tests (aliases: test, testing)
polish (aliases: cleanup, clean)
polish-auto (aliases: auto, auto-polish)
review (aliases: code-review)
build (aliases: feature, feature-dev)
commit (aliases: commit-message)
root-cause (aliases: rca, debug, 5-whys)
deps (aliases: check-deps, dependencies)
review-pr (aliases: pr-review, ultra-review)
mallware-check (aliases: malware, malware-check, scan)
brainstorm (aliases: ideas, ideate)
review-loop (aliases: audit, audit-loop)
team-forming (aliases: form-team, team, compose-team)

Step 1: Context Detection (silent — never print raw output)

Run these commands and store the results internally:

git diff --stat HEAD
git branch --show-current
test -f Cargo.toml && echo "rust"
test -f package.json && echo "typescript"
test -f pyproject.toml && echo "python"
test -f setup.py && echo "python"

Extract:

CHANGES_COUNT: number of changed files (0 if clean)
BRANCH: current branch name
LANGUAGES: list of detected languages
ON_MAIN: true if branch is main or master

Step 2: Present Overview (skip if DIRECT_MODE)

Print the overview table and a context-based recommendation.

## xorio workflows

| # | Workflow | What it does | Command |
|---|----------|-------------|---------|
| 1 | Test | Analyze coverage gaps, detect anti-patterns, generate idiomatic tests | `/xorio:tests` |
| 2 | Polish | 9-step pipeline: simplify → cleanup → review → security audit → validate | `/xorio:polish` |
| 3 | Polish Auto | Autonomous polish loop — runs until clean or max iterations | `/xorio:polish --auto` |
| 4 | Review | Multi-agent review with user decision point — PR review → code review → simplify | `/xorio:review` |
| 5 | Build | Guided feature development — architecture analysis → implementation blueprint | `feature-dev:feature-dev` |
| 6 | Commit | Generate a conventional commit message from current changes (read-only) | `/xorio:commit-message` |
| 7 | Root Cause | 5 Whys analysis — trace a problem to its root cause | `/xorio:root-cause` |
| 8 | Check Deps | Verify required plugins and MCP servers are installed | `/xorio:check-deps` |
| 9 | Review PR | Deep multi-agent PR review — adversarial validation, verified fixes, looped to convergence | `/xorio:review-pr` |
| 10 | Malware Check | Recursive scan for malware, obfuscation, call-home, prompt injection | `/xorio:mallware-check` |
| 11 | Brainstorm | Multi-agent ideation — ideate across lenses → refute → debate → ranked report | `/xorio:brainstorm` |
| 12 | Review Loop | Multi-round audit loop — finders → adversarial verify → fix → repeat until dry | `/xorio:review-loop` |
| 13 | Team Forming | Compose & spawn an agent team for a task-group — architect plans + composes → plan-review gate → verification roles | `/xorio:team-forming` |

Read the full file on GitHub · 362 lines

Changes

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.

4d ago First seen · 362 lines · 14 tokens per session scan A af53f38b814b

Subscribe to this mod's changes

guide is a command published in the GitHub repository radumarias/xorio-claude-plugin (3 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 3,866 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

guide

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Guide Command

Argument Parsing

Step 1: Context Detection (silent — never print raw output)

Step 2: Present Overview (skip if DIRECT_MODE)

What this file has done since we first saw it

Other commands, from other repositories

git

checklist

clarify

specify

converge

implement