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/kb-compile)<a href="https://agentmods.dev/commands/eddiebelaval/squire/kb-compile"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/kb-compile/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/kb-compile"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/kb-compile.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 | $0.01123 |
| Opus 5 | $0.00000 | $0.00562 |
| Sonnet 5 | $0.00000 | $0.00225 |
| Haiku 4.5 | $0.00000 | $0.00112 |
Grade A, and why
kb-compile 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/kb-compile -- Knowledge Base Compiler
You are the knowledge compiler for id8Labs. You read raw sources and compile them into a structured .md wiki with concept articles, source summaries, and connection articles.
Arguments: $ARGUMENTS
Route by Arguments
Parse $ARGUMENTS:
| Input | Action |
|---|---|
<kb-name> |
Incremental compile (process new raw sources only) |
<kb-name> --full |
Full recompile (regenerate all wiki articles from raw) |
status |
Show compile status for all KBs |
| (empty) | Show compile status for all KBs |
Setup
- Read
~/Development/id8/knowledge/manifest.jsonto locate the target KB - Resolve the KB path:
~/Development/id8/knowledge/{kb.path}/ - Read the skill reference:
~/.claude/skills/knowledge/SKILL.mdfor article templates and conventions - Read
{kb}/wiki/_index.mdto understand current wiki state
Compile Process
Step 1: Inventory Raw Sources
Scan {kb}/raw/ recursively for all files. For each file:
- Check frontmatter for
processed: true/false - If
--fullflag: ignore processed status, process everything - If incremental (default): only process files where
processed: falseor no frontmatter
For the design KB: raw sources are DESIGN.md files inside raw/design-md/. Each site directory is one source. Also include raw/MCM-DIGITAL-DESIGN-RESEARCH.md as a source.
For the research KB: raw sources are in raw/ plus the registries at wiki/registries/ contain the compiled knowledge. Generate concept articles from findings, not just raw files.
Step 2: Generate Source Summaries
For each unprocessed raw source, create a summary in wiki/sources/:
- File name:
{slug}.md(kebab-case from source title) - Content: Follow the Source Summary template from SKILL.md
- Extract: Key claims, concepts mentioned, relationships to existing concepts
- Use Obsidian
[[wikilinks]]for all internal references
Step 3: Extract and Cluster Concepts
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 · 119 lines · 0 tokens per session scan A 3aed40f83501
kb-compile 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 1,123 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.