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/spideynolove/claude-dotfilesWrote 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/spideynolove/claude-dotfiles/xia-group)<a href="https://agentmods.dev/commands/spideynolove/claude-dotfiles/xia-group"><img src="https://agentmods.dev/badge/commands/spideynolove/claude-dotfiles/xia-group.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.01435 |
| Opus 5 | $0.00013 | $0.00718 |
| Sonnet 5 | $0.00005 | $0.00287 |
| Haiku 4.5 | $0.00003 | $0.00144 |
Grade B, and why
xia-group scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/xia/groups/xia-group-$GROUP_NAME.md 2>/dev/null || echo "GROUP_MISSING" How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/xia-group — Sequential Group Distillation
Purpose: Run /xia rounds against a ranked list of repos, using the codebase itself as the running distillation. Each round absorbs only what the previous rounds haven't already covered.
Core rule: You never compare two external repos directly. The codebase is always side A. Each round updates A before the next comparison begins.
Usage
/xia-group <group-name> <repo1> <repo2> ... [--focus <topic>]
<group-name>: label for this group run (e.g.autonomous-loops)<repo1> <repo2> ...: repos in order — richest/most complex first, simplest last--focus <topic>: optional, passed to each/xiaround as its focus
Example:
/xia-group autonomous-loops ralph-claude-code ralphex ralphy sleepless-agent claude-auto-resume --focus loop
Storage
Group state is stored alongside xia patterns:
<project-root>/
└── .claude/
└── xia/
├── XIALOGUE.md
├── groups/
│ └── xia-group-[name].md ← group progress file
└── patterns/
└── xia-[repo-slug]-[pattern].md
Ordering Rule
Before running any round, sort the repo list:
- Richest/most complex first (most patterns, highest token count)
- Simplest/most specific last
Rationale: by round N, the simple repos will mostly register as "already covered" — which is the signal that distillation is working.
Phase G0 — Group Init
Commands:
# 1. Check for prior group state
cat .claude/xia/groups/xia-group-$GROUP_NAME.md 2>/dev/null || echo "GROUP_MISSING"
# 2. Check prior XIALOGUE state
cat .claude/xia/XIALOGUE.md 2>/dev/null || echo "XIALOGUE_MISSING"
If GROUP_MISSING, create .claude/xia/groups/xia-group-[name].md with this exact structure:
# Group: [name]
**Focus:** [focus or "none"]
**Started:** [YYYY-MM-DD]
## Round Log
| Round | Repo | Status | Borrowed | Already Covered | Skipped |
|-------|------|--------|----------|-----------------|---------|
## Remaining
[ordered repo list, one per line]
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.
- 6d ago First seen · 210 lines · 25 tokens per session scan B 445b95f4bcb4
xia-group is a command published in the GitHub repository spideynolove/claude-dotfiles (2 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 1,435 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
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
review-sdk-app
Review and validate a Claude Agent SDK application against best practices.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
security-review
AI-powered security review of the current git diff (or specified paths). Dispatches the security-reviewer agent and prints findings grouped by severity.