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.
npx agentmods add commands/eddiebelaval/squire/distrogit clone --depth 1 https://github.com/eddiebelaval/squireWrote 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/eddiebelaval/squire/distro)<a href="https://agentmods.dev/commands/eddiebelaval/squire/distro"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/distro.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 | $0.00000 | $0.05541 |
| Opus 5 | $0.00000 | $0.02771 |
| Sonnet 5 | $0.00000 | $0.01108 |
| Haiku 4.5 | $0.00000 | $0.00554 |
Grade A, and why
distro 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 592 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/distro — Marketing & Distribution Pipeline
You are executing the DISTRO Pipeline — the marketing/distribution counterpart to the ID8 Build Pipeline. This pipeline takes a shipped (or near-shipped) product and creates a systematic path to end users.
Philosophy: The same discipline that builds the product must ship the product. No ad-hoc marketing. No "I'll post something later." Structure creates distribution momentum.
Arguments
/distro— Start from Stage 1 on current project (auto-detect from cwd or ask)/distro --stage N— Jump to a specific stage (for resuming)/distro --status— Show current pipeline status/distro --sustain— Run the weekly sustain cycle (Stage 6)/distro --measure— Run measurement check (Stage 7)/distro --heal— Run the self-healing loop on underperforming assets
Pre-Flight
Before starting, gather context:
- Identify the project — Check cwd, ask if ambiguous. Confirm project name and repo.
- Check for existing distro workspace — Look for
workspace/distro/in the project root. If it exists, readworkspace/distro/DISTRO_STATUS.mdand resume from current stage. - Check build status — Read
PIPELINE_STATUS.mdorBUILDING.mdif they exist. The product should be at Stage 9+ (Launch Prep) or already live. If it's earlier, warn: "This product isn't shipped yet — distro pipeline works best on shipped products. Continue anyway?" - Create distro workspace if it doesn't exist — Run
~/.claude/generators/new-distro-workspace.sh --project <name>or create the structure manually.
The 7 Stages
Stage 1: Product Intel (Automated)
Gate: You can explain the product in one paragraph to a stranger. Checkpoint: "What does this do, who is it for, and why should they care?"
Actions:
- Read the codebase to understand the product:
package.json— name, description, dependencies (reveals stack)README.md/BUILDING.md— product story, what was built- Landing page / home page components — existing copy, messaging
- Route structure — what features exist
- Any existing marketing copy, meta tags, OG images
.env.exampleor deployment config — what's the live URL?
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.
- 3d ago First seen · 592 lines · 0 tokens per session scan A afeea441c888
distro is a command published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,541 tokens. 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 2026-08-30.
Other commands, from other repositories
paul:help
Show available PAUL commands and usage guide.
expect
Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…
kill-mutants
Analyze surviving mutants from a mutation testing run and write targeted unit tests to kill them. Re-runs mutations to confirm kills.
van
Command "van" from vanzan01/claude-code-sub-agent-collective, covering /van - collective routing engine, 🎯 purpose - smart routing, 🚐 routing flow, 🚀 dual-mode routing protocol and 🧠 immediate agent routing.
doncheli-status
Show current project status — phase, progress, coverage, gates.
sugar-task
Create a comprehensive Sugar task with rich context and metadata.