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.
npx agentmods add skills/jbwinters/jacquard-lang/docsnpx skills add jbwinters/jacquard-lang --skill docsgit clone --depth 1 https://github.com/jbwinters/jacquard-langWrote 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/skills/jbwinters/jacquard-lang/docs)<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>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 | $0.00072 | $0.09787 |
| Opus 5 | $0.00036 | $0.04894 |
| Sonnet 5 | $0.00014 | $0.01957 |
| Haiku 4.5 | $0.00007 | $0.00979 |
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 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
--allowgrants. - Probability is the ordinary
Disteffect. 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.
multioperations bind reusable continuations;onceoperations bind affineResumevalues 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.
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.
- ast.md 25 KB
- benchmarks.md 9.2 KB
- ci-cd.md 16 KB
- client-playground.md 7.9 KB
- concurrency.md 55 KB
- development-plan.md 28 KB
- effect-linearity.md 14 KB
- effect-membranes.md 95 KB
- effect-review.md 6.0 KB
- effect-taxonomy.md 37 KB
- errors.md 41 KB
- example-code.md 3.6 KB
- host-boundary.md 18 KB
- native-compilation.md 20 KB
- native-intrinsics.md 3.8 KB
- native-parallel-decision.md 7.4 KB
- native-plan.md 45 KB
- perf-roadmap.md 6.5 KB
- perf-vm-decision.md 8.4 KB
- README.md 21 KB
- relational-warp.md 22 KB
- release/0.1/CLAIMS.md 5.9 KB
- release/0.1/DECISION.md 1.5 KB
- release/0.1/EVIDENCE.md 5.7 KB
- release/0.1/FREEZE.md 4.2 KB
- release/0.1/GAUNTLET.md 4.0 KB
- release/0.1/LIMITS.md 5.7 KB
- release/0.1/RELEASE-NOTES.md 2.6 KB
- release/0.1/REPRO.md 3.5 KB
- release/0.2/CLAIMS.md 4.4 KB
- release/0.2/DECISION.md 1.8 KB
- release/0.2/EVIDENCE.md 3.9 KB
- release/0.2/FREEZE.md 1.7 KB
- release/0.2/GAUNTLET.md 2.3 KB
- release/0.2/LIMITS.md 3.8 KB
- release/0.2/MANIFEST.sha256 2.7 KB
- release/0.2/RELEASE-NOTES.md 2.0 KB
- release/0.2/REPRO.md 2.5 KB
- release/dx-jac-export/DECISION.md 3.2 KB
- release/dx-jac-export/EVIDENCE.md 5.8 KB
- release/dx-parser-performance/EVIDENCE.md 3.0 KB
- release/effect-linearity/EVIDENCE.md 15 KB
- release/effect-linearity/MANIFEST.sha256 29 KB
- release/effect-taxonomy/ET3-EVIDENCE.md 4.1 KB
- release/effect-taxonomy/ET3-MANIFEST.sha256 24 KB
- release/effect-taxonomy/ET4-EVIDENCE.md 3.5 KB
- release/effect-taxonomy/ET4-MANIFEST.sha256 23 KB
- release/effect-taxonomy/ET5-EVIDENCE.md 3.2 KB
- release/effect-taxonomy/ET5-MANIFEST.sha256 23 KB
- release/effect-taxonomy/ET6-EVIDENCE.md 4.1 KB
- release/effect-taxonomy/ET6-MANIFEST.sha256 23 KB
- release/effect-taxonomy/ET7-EVIDENCE.md 2.5 KB
- release/effect-taxonomy/ET7-MANIFEST.sha256 23 KB
- release/effect-taxonomy/ET8-EVIDENCE.md 5.1 KB
- release/effect-taxonomy/ET8-MANIFEST.sha256 22 KB
- release/effect-taxonomy/EVIDENCE.md 3.2 KB
- release/effect-taxonomy/MANIFEST.sha256 24 KB
- release/explicit-dictionaries/DECISION.md 3.8 KB
- release/explicit-dictionaries/EVIDENCE.md 2.1 KB
- release/governed-membranes/CLAIMS.md 11 KB
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 · 949 lines · 72 tokens per session scan C 839b45e66f94
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.
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.
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.
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.
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.
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.
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…