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/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-lexicon)<a href="https://agentmods.dev/commands/eddiebelaval/squire/distro-lexicon"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/distro-lexicon.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 | $0.00000 | $0.06039 |
| Opus 5 | $0.00000 | $0.03019 |
| Sonnet 5 | $0.00000 | $0.01208 |
| Haiku 4.5 | $0.00000 | $0.00604 |
Grade A, and why
distro-lexicon 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 8d 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 — 583 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DISTRO Lexicon — Best Practices & Strategy Reference
This is the knowledge base for the DISTRO Pipeline. Consult this when generating assets (Stage 3), diagnosing underperformance (Stage 7), or running the self-healing loop (/distro --heal).
How to use: Each section covers one asset type. Each has: frameworks, rules, anti-patterns, benchmarks, and platform-specific gotchas. When an asset underperforms, cross-reference its type here to diagnose the failure mode.
Table of Contents
- Universal Principles
- X / Twitter
- Product Hunt
- Hacker News
- Landing Pages
- Blog Posts & Long-Form
- Paid Ads
- Copywriting Frameworks
- Failure Mode Taxonomy
Universal Principles
These apply to EVERY asset type. Violating any of these is the most common cause of underperformance.
The 5 Laws of Distribution
- Specificity beats generality. "For couples navigating conflict" beats "for everyone." Narrow targeting always outperforms broad.
- Benefits beat features. "Resolve arguments without a therapist" beats "AI-powered mediation tool." People buy outcomes, not technology.
- One message per asset. Never try to communicate two things at once. One post = one idea. One email = one CTA.
- Social proof is the multiplier. Every asset performs better with evidence: "500 couples used this" > "Try our new tool." If you don't have numbers, use specificity: "Anna resolved a 3-week argument in one session."
- The first line does all the work. 80% of performance is determined by the hook (first line of a post, subject line of an email, headline of a page). If the hook fails, nothing else matters.
The Anti-Pattern Checklist
Before shipping ANY asset, check for these killers:
- Corporate voice — sounds like a press release instead of a human
- Feature dumping — listing features instead of painting outcomes
- No hook — the first line is boring, generic, or introduces the product before the problem
- Multiple CTAs — asking the reader to do more than one thing
- No urgency or curiosity — nothing makes the reader feel they'll miss out or need to know more
- Talking to everyone — so broad it resonates with nobody
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.
- 8d ago First seen · 583 lines · 0 tokens per session scan A 568fcf84dcfa
distro-lexicon is a command published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,039 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.
kill-mutants
Analyze surviving mutants from a mutation testing run and write targeted unit tests to kill them. Re-runs mutations to confirm kills.
analizar-sesiones
Analizar sesiones de Claude en el equipo para extraer patrones de uso y generar recomendaciones de habilidades, plugins, agentes y reglas.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
iniciar
Inicializar Don Cheli en un proyecto nuevo o existente.
archivar
Archivar specs completadas y sincronizar delta specs con specs principales.