agentmods.dev

blitzdenk AGENTS.md

blitzdenk AGENTS.md is an instructions file for Codex, OpenCode from Lommix/blitzdenk. It costs 1,101 tokens per session, scanned A, original, MIT.

A project-specific instruction file for Blitzdenk, a coding harness written in Zig with embedded Lua. It records the code layout, supported model types, and important rules for Zig 0.16.

In plain words
What is it for?
Use it when working on Blitzdenk’s agent state, terminal interface, Lua or MCP integrations, hot reload, skills, tools, or model configuration.
Why use it?
It gives a coding agent the project context it needs before changing code. This reduces mistakes caused by using the wrong module, command, API, or Zig behavior.

Instructions file for CodexOpenCode

not rated 10 3d ago A scan 1,101 tokens original MIT
View the source file Lommix/blitzdenk
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 instructions/lommix/blitzdenk/agents-md
Clone the repo
git clone --depth 1 https://github.com/Lommix/blitzdenk

Made for: Codex, OpenCode.

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 blitzdenk AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lommix/blitzdenk/agents-md.svg)](https://agentmods.dev/instructions/lommix/blitzdenk/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/lommix/blitzdenk/agents-md"><img src="https://agentmods.dev/badge/instructions/lommix/blitzdenk/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,101 This file is loaded in full into every session.
When invoked 1,101 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.01101 $0.01101
Opus 5 $0.00550 $0.00550
Sonnet 5 $0.00220 $0.00220
Haiku 4.5 $0.00110 $0.00110

Measured 3d ago against content hash 21ca4d66c503, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

blitzdenk 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 3d 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.

AGENTS.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Blitzdenk

A coding harness written in Zig with vendored Lua. Zig version: 0.16

Important modules:

  • src/root.zig import hub; everything is reached via the r.* namespace
  • src/agent_id.zig AgentId packed struct {index: u16, generation: u16}; pack()/unpack() bitcast to u32
  • src/main.zig control flow, owns the hot-reload loop
  • src/app.zig main tui state and render; applyRunEvent turns stream events into chat preview
  • src/tui tui lib and common widgets
  • src/tools agent tool definitions
  • src/lua.zig the lua bindings, big file; the whole blitz.* api is one declarative Blitz table_def
  • src/mcp.zig the mcp api and tools.
  • src/context_factory.zig agent and prompt configuration; system prompt built per configureAgent
  • src/skills.zig skill loading and management
  • src/exec.zig shell wrapper
  • src/keys.zig key bindings
  • src/models.zig model config; Model union over provider kinds ollama/openai/response/anthropic
  • src/agent.zig the agent state; Activity enum and observe() derive status/stream state
  • src/agent_run.zig run task + event queue bridging sdk streams to observers
  • src/agent_registry.zig state management for many agents; drain() fans events out
  • src/commands.zig async command queue.
  • src/inject.zig agent status injections
  • src/session.zig save/load session state; SaveState/WireToolStatus shared by store checkpoint and blitz continue
  • src/session_store.zig JSONL session journals in ~/.cache/blitzdenk/<fnv1a64-of-cwd>/sessions/<id>.jsonl (header + full-snapshot checkpoints, cap 4, tmp+rename compaction, GC >16d); blitz continue [ID], blitz sessions (TUI session picker over summaries() rows; widget state in src/session_picker.zig, rendered like the wizard) and the exit hint in main.zig use it; debug.log also lives in ~/.cache/blitzdenk; cacheDir() honors XDG_CACHE_HOME over ~/.cache
  • src/compact.zig chat compaction logic
  • src/events.zig exposed hooks
  • src/defaults.zig installs default config files into ~/.config/blitzdenk
  • sdk/ the blitz-sdk ai provider library
  • sdk/src/provider/ one file per provider: openai.zig chat completions, responses.zig Responses API, anthropic.zig, compat.zig; jsonx.zig http + SSE plumbing

Read the full file on GitHub · 55 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. 3d ago First seen · 55 lines · 1,101 tokens per session scan A 21ca4d66c503

Subscribe to this mod's changes

blitzdenk AGENTS.md is an instructions file published in the GitHub repository Lommix/blitzdenk (10 stars, last pushed 3d ago), licensed MIT. It adds 1,101 tokens to every session, about $0.0055 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 2026-08-31.

LLMai-agentscoding-agentharnessluazig
Related

Other instructions, from other repositories

Albatross AGENTS.md

Instructions for morganlinton/Albatross, covering agent instructions, general and releases.

morganlinton/Albatross · 454 tokens

sail CLAUDE.md

Instructions for standardapplied/sail, covering claude.md, why sail exists, tech stack, infrastructure inside containers and conventions.

standardapplied/sail · 2,067 tokens

lunar AGENTS.md

Instructions for gszr/lunar, covering how to work here, our goals, before you type, code and scope.

gszr/lunar · 459 tokens

superturtle CLAUDE.md

Instructions for Rigos0/superturtle, covering superturtle user notes, latest release highlights, important migration info, common commands and notes for the turtle.

Rigos0/superturtle · 324 tokens

wezterm-ai-agents CLAUDE.md

Instructions for nakashima-takeo/wezterm-ai-agents, covering claude.md, 概要, コマンド, lint and フォーマットチェック.

nakashima-takeo/wezterm-ai-agents · 1,655 tokens

superturtle AGENTS.md

Instructions for Rigos0/superturtle, a project described as: Coding agent on your phone 🐢.

Rigos0/superturtle · 4 tokens