jacquard

jacquard is a skill for Claude Code, Codex from jbwinters/jacquard-lang. It costs 72 tokens per session (9,787 once invoked), scanned C, original, Apache-2.0.

A programming language and toolkit for writing programs whose effects, randomness, permissions, and structural identity are checked explicitly.

In plain words
What is it for?
Use it to write, format, test, compile, and run Jacquard programs, including probabilistic models, capability manifests, handlers, and native builds.
Why use it?
It makes operations such as network access and uncertainty visible to the checker, while supporting reproducible identity and testing of programs.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/jbwinters/jacquard-lang/docs
Any agent
npx skills add jbwinters/jacquard-lang --skill docs
Clone the repo
git clone --depth 1 https://github.com/jbwinters/jacquard-lang

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for jacquard

README.md
[![agentmods](https://agentmods.dev/badge/skills/jbwinters/jacquard-lang/docs.svg)](https://agentmods.dev/skills/jbwinters/jacquard-lang/docs)
Your own site
<a href="https://agentmods.dev/skills/jbwinters/jacquard-lang/docs"><img src="https://agentmods.dev/badge/skills/jbwinters/jacquard-lang/docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,787 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00072 $0.09787
Opus 5 $0.00036 $0.04894
Sonnet 5 $0.00014 $0.01957
Haiku 4.5 $0.00007 $0.00979

Measured 5d ago against content hash 839b45e66f94, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

jacquard scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/jbwinters/jacquard-lang/jacquard-core-0.2.0/scripts/install.sh | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://raw.githubusercontent.com/jbwinters/jacquard-lang/jacquard-core-0.2.0/scripts/install.sh | sh
docs/SKILL.md · 949 lines

How it starts

The opening of the file, as written. The whole thing — 949 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Jacquard Standalone Guide

Jacquard is a research language for model-written, human-reviewed programs. Its central promise is that effects, uncertainty, and program identity remain visible to the checker and tools:

  • Function arrows carry effect rows, such as (Text) ->{Net, Console} Int.
  • A runnable expression's inferred row is its authority manifest. The runtime installs world handlers only for explicit --allow grants.
  • Probability is the ordinary Dist effect. Exact enumeration and likelihood weighting run the same model under different handlers.
  • Definitions are content-addressed from canonical resolved structure after comments, formatting, spans, provenance, and ordinary local or term names are erased. This structural identity is not arbitrary program equivalence.
  • Handlers are deep. multi operations bind reusable continuations; once operations bind affine Resume values with static and runtime reuse checks.

This file is self-contained for public use. A repository checkout is needed only to develop the OCaml implementation, not to install or write Jacquard.

Install

The release installer downloads a checksum-verified binary, the standard prelude, demos, and the C runtime used by native builds. It does not require OCaml, opam, or Dune.

curl -fsSL https://raw.githubusercontent.com/jbwinters/jacquard-lang/jacquard-core-0.2.0/scripts/install.sh | sh
export PATH="$HOME/.local/bin:$PATH"
jac --version
jac run "$HOME/.local/share/jacquard/demos/basics/m1-fact.jac"
sh "$HOME/.local/share/jacquard/demos/case-studies/release-risk/run.sh"

The jac run command prints 120; the final command runs the larger release risk narrative. The published targets are Linux x86-64, macOS Intel, and macOS Apple Silicon. Set JACQUARD_INSTALL_PREFIX to choose a different prefix and JACQUARD_INSTALL_VERSION to choose another release tag. The long command is jacquard; jac is its installed short alias.

Shipped *.sh demo launchers work without a source checkout. Use them for models that require an inference driver and for multi-file narratives; directly running an observe model under jac run correctly fails with E0904.

Read the full file on GitHub · 949 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 5d ago First seen · 949 lines · 72 tokens per session scan C 839b45e66f94

Subscribe to this mod's changes

jacquard is a skill published in the GitHub repository jbwinters/jacquard-lang (116 stars, last pushed 9d ago), licensed Apache-2.0. It adds 72 tokens to every session and 9,787 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

pymc-bayesian-modeling

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

synthetic-sciences/openscience · 48 tokens

vera-language

Write programs in the Vera programming language. Use when asked to write, edit, debug, or review Vera code (.vera files). Vera is a statically typed, purely functional language with algebraic effects, mandatory contracts, and typed slot references (@T.n) instead of variable names.

aallan/vera · 61 tokens

sema-usage

Content-addressed vocabulary protocol via the sema MCP server. Use when working with shared vocabulary — searching, resolving, minting, and verifying meaning across agents and conversations.

emergent-wisdom/sema · 39 tokens

sema-mint

How to mint new sema patterns — the full pipeline from concept to content-addressed vocabulary entry. Covers required fields, dependency wiring, validation rules, and the hashing model.

emergent-wisdom/sema · 43 tokens

vera-language

Write programs in the Vera programming language. Use when asked to write, edit, debug, or review Vera code (.vera files). Vera is a statically typed, purely functional language with algebraic effects, mandatory contracts, and typed slot references (@T.n) instead of variable names.

aallan/vera · 61 tokens

sema-seed

Seed the sema vocabulary by exploring random words. Pull a word from the system dictionary, think about it through the sema lens without forcing it into a pattern, then mint only if a genuinely useful and distinct pattern emerges. Use when the user asks to "seed", "expand", "grow", or "explore new patterns for" the…

emergent-wisdom/sema · 79 tokens