edict-compiler-dev

edict-compiler-dev is a skill for Claude Code, Codex from Sowiedu/Edict. It costs 100 tokens per session (2,231 once invoked), scanned A, original, MIT.

A development guide for Edict, a programming language designed for AI agents that produce JSON syntax trees. Its compiler validates those trees, resolves names, checks types, and returns structured errors that an agent can use to correct its output.

In plain words
What is it for?
Use it when adding syntax-tree node types or built-ins, changing compiler stages, fixing bugs, or extending the Edict TypeScript codebase.
Why use it?
It gives contributors the architecture and design boundaries needed to add features without introducing human-oriented syntax or error handling that conflicts with Edict's approach.

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/sowiedu/edict/edict-compiler-dev
Any agent
npx skills add Sowiedu/Edict --skill edict-compiler-dev
Clone the repo
git clone --depth 1 https://github.com/Sowiedu/Edict

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 edict-compiler-dev

README.md
[![agentmods](https://agentmods.dev/badge/skills/sowiedu/edict/edict-compiler-dev.svg)](https://agentmods.dev/skills/sowiedu/edict/edict-compiler-dev)
Your own site
<a href="https://agentmods.dev/skills/sowiedu/edict/edict-compiler-dev"><img src="https://agentmods.dev/badge/skills/sowiedu/edict/edict-compiler-dev.svg" alt="Measured on agentmods" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,231 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00100 $0.02231
Opus 5 $0.00050 $0.01115
Sonnet 5 $0.00020 $0.00446
Haiku 4.5 $0.00010 $0.00223

Measured 5d ago against content hash 7b1054063c54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

edict-compiler-dev scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- `NodeHostAdapter` — default, uses `node:crypto`, `node:fs`, `node:child_process`
.agent/skills/edict-compiler-dev/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Edict Compiler Development

Edict is a programming language designed exclusively for AI agents. Agents produce JSON AST, the compiler validates and returns structured errors, the agent self-repairs. No human in the loop.

Critical Philosophy — The North Star

"If no human ever saw this, would I still build it this way?"

Edict's moat is the bet that a language designed for agent cognition beats any language designed for human cognition. Every human-centric feature erodes this moat.

Never build: text syntax/parser, human-readable error messages, CLI for human use, pretty-printer, IDE/LSP integration, comments in AST, web playground/REPL.

Priority order: (1) minimize agent-compiler round-trips, (2) error actionability, (3) token efficiency, (4) correctness surface.

Read .agent/rules/criticalrules.md for the full set of hard boundaries.


Architecture

src/
├── ast/           # TypeScript interfaces for every AST node (nodes.ts, types.ts)
├── validator/     # Phase 1: Schema validation (structural correctness)
├── resolver/      # Phase 2a: Name resolution (scope-aware, Levenshtein suggestions)
├── checker/       # Phase 2b: Type checking (bidirectional, unit types)
├── effects/       # Phase 3: Effect checking (call-graph propagation)
├── contracts/     # Phase 4: Contract verification (Z3/SMT integration)
├── codegen/       # Phase 5: WASM code generation (pure-JS encoder)
│   ├── codegen.ts    # AST → WASM compilation
│   ├── runner.ts     # WASM execution (Node.js WebAssembly API)
│   ├── builtins.ts   # Built-in functions (print, string ops)
│   └── string-table.ts  # String interning for WASM memory
├── mcp/           # Phase 6: MCP server (tools + resources)
│   ├── create-server.ts  # Tool/resource registration
│   ├── handlers.ts       # Tool handler implementations
│   └── server.ts         # Entry point (stdio + HTTP/SSE transports)
├── errors/        # Structured error types and constructors
│   └── structured-errors.ts
├── check.ts       # Full pipeline orchestrator (validate → resolve → check → effects → contracts)
├── compile.ts     # Compile + run convenience wrapper
└── index.ts       # Public API exports

Read the full file on GitHub · 180 lines

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 · 180 lines · 100 tokens per session scan A 7b1054063c54

Subscribe to this mod's changes

edict-compiler-dev is a skill published in the GitHub repository Sowiedu/Edict (11 stars, last pushed 7d ago), licensed MIT. It adds 100 tokens to every session and 2,231 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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

automatic-differentiation-advanced

Extend Sounio's automatic differentiation capabilities to higher‑order derivatives, Hessians, differentiation through control flow, and GPU‑accelerated gradient computation, enabling state‑of‑the‑art scientific machine learning.

Sounio-lang/sounio · 50 tokens

epistemic-uncertainty-quantification

Extend Sounio's epistemic types with advanced uncertainty quantification methods, such as confidence intervals, non‑Gaussian distributions, and Dempster‑Shafer evidence combination, positioning the language at the state‑of‑the‑art in measurement science.

Sounio-lang/sounio · 62 tokens

formal-verification-epistemic

Integrate formal verification tools (SMT solvers, Lean) to prove properties of epistemic programs, such as uncertainty bounds, confidence guarantees, and provenance integrity, establishing Sounio as a language with mathematically verified scientific claims.

Sounio-lang/sounio · 55 tokens

sounio-pgo

Work on the profile-guided optimization pipeline: counter injection, .sprof file output, strategy promotion, inlining, layout, const-fold/DCE, and register allocation; use when editing any sprint 38–52+ IR optimization files.

Sounio-lang/sounio · 55 tokens

safe-refactoring

Perform systematic, safety‑preserving refactoring of code in any language, using dependency analysis, invariant detection, and verification techniques to avoid introducing bugs.

Sounio-lang/sounio · 34 tokens

sounio-bootstrap

Work on the self-hosted Sounio compiler bootstrap path: self-hosted/main.sio pipeline modes (--lex, --parse, --check, --ir-dump, --native-compile), frontend corpus gates, and bootstrap binary milestones.

Sounio-lang/sounio · 54 tokens