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/sowiedu/edict/edict-compiler-devnpx skills add Sowiedu/Edict --skill edict-compiler-devgit clone --depth 1 https://github.com/Sowiedu/EdictWrote 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/sowiedu/edict/edict-compiler-dev)<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>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 | $0.00100 | $0.02231 |
| Opus 5 | $0.00050 | $0.01115 |
| Sonnet 5 | $0.00020 | $0.00446 |
| Haiku 4.5 | $0.00010 | $0.00223 |
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` 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
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 · 180 lines · 100 tokens per session scan A 7b1054063c54
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.
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.
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.
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-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.
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-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.