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/publish)<a href="https://agentmods.dev/commands/eddiebelaval/squire/publish"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/publish/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/eddiebelaval/squire/publish"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/publish.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 | $0.00000 | $0.06674 |
| Opus 5 | $0.00000 | $0.03337 |
| Sonnet 5 | $0.00000 | $0.01335 |
| Haiku 4.5 | $0.00000 | $0.00667 |
Grade A, and why
publish 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 5d 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 — 674 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/publish — Editorial Pipeline
Run a manuscript through a 6-agent editorial pipeline. Takes a raw manuscript (typically from /write-article or a collaborative writing session) and sends it through professional-grade editorial review: developmental editing, cross-domain validation, line editing, copy editing, voice authentication, and fresh-eyes final read.
Arguments
- $ARGUMENTS: File path to the manuscript OR "last article" to use the most recently written article. Can also be a brief description to search for.
Instructions
Phase 1: Locate the Manuscript
Find and read the target manuscript. Common locations:
~/Development/id8/id8labs/content/essays/*.mdx(published articles)~/Development/artifacts/id8labs/*.md(draft research papers)~/Development/id8/products/parallax/docs/**/*.md(Parallax docs)- Specific file path provided by user
Read the FULL manuscript. Understand what it is — research paper, essay, thought leadership, technical write-up. Note the genre, because each agent calibrates to it.
Phase 2: Build Context Package
Before spawning agents, assemble the context they all need:
- The manuscript (full text)
- Genre classification: research paper | essay | thought leadership | technical writeup | release notes
- Eddie's voice profile (embed this in every agent prompt):
- First person, casual but precise
- Builder energy — "ship fast, iterate faster"
- Credits collaborators generously
- Concrete examples over abstract theory
- Shows messy reality, not polished perfection
- Technical but accessible — explain WHY, not just WHAT
- Ends with what's next — always building toward something
- Uses repetition as rhetorical device ("what's next?" recurring in CaF.ii)
- Section endings often echo or callback to earlier phrases
- Target audience: Builders, founders, researchers, technically curious non-specialists
- id8Labs brand voice: Professional but human. Confident but curious. Never corporate. Never academic-stiff.
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.
- 5d ago First seen · 674 lines · 0 tokens per session scan A 88c5c355d741
publish is a command published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,674 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 2026-09-03.
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.