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 instructions/jbwinters/jacquard-lang/agents-mdgit 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/instructions/jbwinters/jacquard-lang/agents-md)<a href="https://agentmods.dev/instructions/jbwinters/jacquard-lang/agents-md"><img src="https://agentmods.dev/badge/instructions/jbwinters/jacquard-lang/agents-md.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 5.1 | $0.01653 | $0.01653 |
| Opus 5 | $0.00826 | $0.00826 |
| Sonnet 5 | $0.00331 | $0.00331 |
| Haiku 4.5 | $0.00165 | $0.00165 |
Grade A, and why
jacquard-lang AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Notes
This repository is an implemented OCaml research prototype in release-hardening mode. Treat it as a semantic artifact with evidence, not as a greenfield language project. Before editing code, read:
README.mddocs/README.mddocs/development-plan.mddocs/ast.mddocs/release/0.2/EVIDENCE.md
The original development plan has been completed. Use Task Master only for local historical context unless the user explicitly asks for it.
task-master next
task-master show <id>
task-master set-status <id> in-progress
task-master validate-dependencies
Tooling
Use asdf only to provide opam. Use the repo-local opam switch for OCaml and OCaml packages.
Run this before OCaml commands in a fresh shell:
eval "$(opam env)"
mkdir -p "$PWD/.scratch/tmp"
export TMPDIR="$PWD/.scratch/tmp"
Keep temporary clones, worktrees, release reproductions, and generated test
stores under .scratch/ in this repository. The root filesystem is small: do
not create Jacquard workspaces or build artifacts under /tmp.
Expected local toolchain:
opam2.5.1 from.tool-versions- OCaml 5.1.1 from the repo-local switch
dunealcotestqcheckdigestifocamlformatmenhircmdlinerocaml-lsp-serverutopodoc
Core commands for the current scaffold:
eval "$(opam env)"
opam exec -- dune build
opam exec -- dune build @all
opam exec -- dune test
opam exec -- dune runtest
opam exec -- dune fmt
git diff --exit-code
opam exec -- dune build @doc
The implementation is in src/ with suites in test/. Verify the environment with:
eval "$(opam env)"
ocaml -version
dune --version
opam exec -- dune build @all
opam exec -- dune runtest
When adding valid corpus files, regenerate the golden hashes with
opam exec -- dune exec test/gen_goldens.exe and commit the diff (see
corpus/README.md).
Working Rules
- Preserve the release-hardening posture unless the user explicitly asks for feature work.
- Start from existing tests and docs. Jacquard behavior is pinned by cram transcripts, Alcotest/QCheck suites, corpus goldens, demos, and release docs.
- Keep behavior tied to the 27 kernel forms in
docs/ast.md. Public.jacsyntax must remain a projection onto those forms, and bootstrap.jqdremains the permanent kernel/debug carrier. - Do not hand-maintain a
.jqdtwin for an ordinary.jacprogram or demo. Add paired carriers only when a conformance test explicitly requires hash or lowering parity; twins are evidence fixtures, not a publishing requirement. - During 0.2 release hardening, do not expand the native/performance scope or add macros beyond quote/unquote/gated eval, records, typed staging, continuous distributions, package management, self-hosting, or ownership/borrowing.
- Use
dune,alcotest, andqcheckfor build and tests. - Use
digestiffor the initial hash implementation unless the owner changes D1. - Use
menhirfor the bootstrap reader if a generated parser is needed. - Use
cmdlinerfor the CLI. - Use
ocamlformatfor formatting once the project has a formatter config. - Public functions in touched modules should have doc comments describing contracts and failure modes.
- Library code should return
('a, Diag.t list) result; exceptions are only for internal invariant failures and should be prefixedBug_.
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.
- 6d ago First seen · 167 lines · 1,653 tokens per session scan A 5e0510711b1f
jacquard-lang AGENTS.md is an instructions file published in the GitHub repository jbwinters/jacquard-lang (118 stars, last pushed today), licensed Apache-2.0. It adds 1,653 tokens to every session, about $0.0083 per session on Opus 5. 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 2026-08-30.
Other instructions, from other repositories
effection AGENTS.md
AGENTS.md instructions for thefrontside/effection, covering agents.md — effection agent contract, core invariants (do not violate), operations vs promises, structured concurrency is scope-owned and effects do not escape scopes.
sounio copilot-instructions.md
Copilot instructions for Sounio-lang/sounio, covering sounio language instructions for github copilot, compiler, critical syntax differences from rust, effects system (required) and variables and types.
hird AGENTS.md
AGENTS.md instructions for no-materials/hird, covering agents.md, north star, non-negotiables (definition of done), before implementing a ticket and rust workspace expectations.
dingtalk-workspace-cli AGENTS.md
AGENTS.md instructions for DingTalk-Real-AI/dingtalk-workspace-cli, covering repository agent guide, build and test, command framework declaration, flag / help / schema homology and agent schema contract.
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.