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/sowiedu/edict/agents-mdgit 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/instructions/sowiedu/edict/agents-md)<a href="https://agentmods.dev/instructions/sowiedu/edict/agents-md"><img src="https://agentmods.dev/badge/instructions/sowiedu/edict/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 | $0.01175 | $0.01175 |
| Opus 5 | $0.00588 | $0.00588 |
| Sonnet 5 | $0.00235 | $0.00235 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
Edict 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 4d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Standard agent-facing entry point for AI agents working with this repository.
What is Edict?
Edict is a programming language designed exclusively for AI agents. Programs are JSON ASTs — no text syntax, no parser. The compiler validates structure, resolves names, checks types and effects, verifies contracts via Z3, and compiles to WebAssembly.
Quick Orientation
| Resource | Path | Purpose |
|---|---|---|
| README | README.md |
Project overview, quick start, architecture |
| Feature Spec | FEATURE_SPEC.md |
Full language specification |
| Roadmap | ROADMAP.md |
Development plan and priorities |
| JSON Schema | schema/edict.schema.json |
AST schema (the spec for writing programs) |
| Examples | examples/ |
41 example programs — see README for difficulty tiers |
| Contributing | CONTRIBUTING.md |
Setup, coding standards, PR workflow |
| Changelog | CHANGELOG.md |
Version history |
Agent Skills (deep-dive guides)
These are detailed skill files for agents that need to go deeper:
| Skill | Path | When to use |
|---|---|---|
| Compiler Dev | .agent/skills/edict-compiler-dev/SKILL.md |
Contributing to the compiler, adding features, fixing bugs |
| Program Writer | .agent/skills/edict-program-writer/SKILL.md |
Writing Edict programs, using MCP tools, debugging errors |
| Testing | .agent/skills/edict-testing/SKILL.md |
Writing tests, running the test suite, coverage patterns |
MCP Server
Edict exposes its full compiler pipeline via Model Context Protocol:
npm run mcp # stdio transport
npx edict-lang # after npm install
Tools: edict_schema, edict_version, edict_examples, edict_validate, edict_check, edict_compile, edict_run, edict_patch, edict_errors, edict_lint, edict_debug, edict_compose, edict_explain, edict_export, edict_import_skill, edict_generate_tests, edict_replay, edict_deploy, edict_invoke, edict_invoke_skill, edict_package, edict_support
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.
- 4d ago First seen · 93 lines · 1,175 tokens per session scan A ae0153320246
Edict AGENTS.md is an instructions file published in the GitHub repository Sowiedu/Edict (11 stars, last pushed 5d ago), licensed MIT. It adds 1,175 tokens to every session, about $0.0059 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
sounio CLAUDE.md
Instructions for Sounio-lang/sounio, covering claude.md, 1. calibration — read before any analysis, 2. project identity, 3. session bootstrap and 4. build & run.
sounio AGENTS.md
Instructions for Sounio-lang/sounio, covering agents.md, steps, purpose, recovery + remote-first bootstrap and repository identity.
sounio copilot-instructions.md
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.
hird CLAUDE.md
Claude Code instructions for no-materials/hird, a project described as: A typed language for LLM agent systems on BEAM: effect-row tracking, auditable tool effects, typed actors, and OTP supervision, queryable by agents over MCP.
oxc AGENTS.md
Instructions for oxc-project/oxc, covering agents.md - ai assistant guide for oxc, ai usage policy for contributors, repository structure, core crates and development commands.