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/thrift)<a href="https://agentmods.dev/commands/eddiebelaval/squire/thrift"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/thrift/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/thrift"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/thrift.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 | $0.01742 |
| Opus 5 | $0.00000 | $0.00871 |
| Sonnet 5 | $0.00000 | $0.00348 |
| Haiku 4.5 | $0.00000 | $0.00174 |
Grade A, and why
thrift 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/thrift - the approach gate
The one question: is this the cheapest mechanism that does the job?
Cheap meaning all four currencies: compute, latency, tokens, dollars. This is the
Model Cascade (~/.claude/docs/model-cascade.md) applied to implementation choice —
work funnels DOWN to the cheapest adequate tier, and a thing built one tier too high
costs that difference forever.
Runs SELF-CONTAINED. No plugin agents (code-simplifier and feature-dev are false
in settings.json).
Where it sits — and why it is FIRST among the change gates
/verify does it work? green baseline, or nothing below is falsifiable
/thrift is this the RIGHT WAY? <- YOU ARE HERE. change the approach
/simplify what can go? shrink what survives
/polish is it finished? add the edges
/assay is it worth keeping? worth
/3pv is it what he asked? intent
The chain runs largest blast radius first. Approach → structure → edges → worth → intent. Thrift can replace a whole mechanism; simplify only reshapes the one it finds; polish only fills its gaps. Running them in any other order means shrinking and finishing code you are about to throw away.
What separates this from /simplify
/simplify works INSIDE the chosen approach and asks whether it could be smaller.
/thrift asks whether the approach is right at all. A simplify pass will happily shave
three lines off a bubble sort and never notice it should be a hash lookup. That gap is
what this gate covers, and it is the only thing it covers.
If a finding makes the code shorter but does not change the mechanism, it belongs to
/simplify. Hand it over rather than doing it here.
Arguments
--files <glob>— restrict to a path. Default: the branch diff vs base.--dry-run— report findings, change nothing.- Empty = the current branch's diff.
Step 0: baseline, and the refusal
npx tsc --noEmit; echo "tsc=$?"
npm test -- --run > /tmp/gate-tests.log 2>&1; echo "tests=$?"; tail -20 /tmp/gate-tests.log
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 · 157 lines · 0 tokens per session scan A c41fa051c69b
thrift 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 1,742 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.