rule-of-textuality

rule-of-textuality is a skill for Claude Code from jonZlotnik/how-to-agent. It costs 51 tokens per session (593 once invoked), scanned A, original, MIT.

A guideline for choosing readable text formats, such as JSON or CSV, for settings, logs, messages between programs, and saved data.

In plain words
What is it for?
It helps decide between text and binary formats and review proposals for logs, storage formats, or communication between programs.
Why use it?
Text can be searched, compared in version control, edited by hand, and read by many tools. Binary formats can hide data and require special software.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the how-to-agent plugin — 27 skills shipped together

Good fit It helps decide between text and binary formats and review proposals for logs, storage formats, or communication between programs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jonzlotnik/how-to-agent/rule-of-textuality
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.

Any agent
npx skills add jonZlotnik/how-to-agent --skill rule-of-textuality
Clone the repo
git clone --depth 1 https://github.com/jonZlotnik/how-to-agent

Made for: Claude Code.

Or install how-to-agent, the plugin that ships this one along with the rest of its 27 skills.

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 rule-of-textuality

README.md
[![agentmods](https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/rule-of-textuality/github.svg)](https://agentmods.dev/skills/jonzlotnik/how-to-agent/rule-of-textuality)
Your own site
<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/rule-of-textuality"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/rule-of-textuality/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for rule-of-textuality

Your own site · 80×15
<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/rule-of-textuality"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/rule-of-textuality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 593 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00051 $0.00593
Opus 5 $0.00026 $0.00296
Sonnet 5 $0.00010 $0.00119
Haiku 4.5 $0.00005 $0.00059

Measured 12d ago against content hash 2f2afabee35b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

rule-of-textuality 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 12d 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.

skills/rule-of-textuality/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rule of Textuality

Plain text is the universal solvent. Anything textual can be grep'd, diff'd, version-controlled, fixed by hand at 3am, and inspected by tools nobody has written yet. Binary formats foreclose all of that for a transient gain — usually one nobody actually measured.

When to use

  • Picking a config or interchange format (text vs binary)
  • Designing a log format, on-disk format, or IPC payload
  • Tempted to introduce protobuf/MessagePack/custom struct dumps for "performance"
  • Reviewing an opaque blob that can only be read by the program that wrote it

Protocol

  1. Pick textual by default — JSON, TOML, YAML, RFC-822 style, CSV, line-record formats. Whatever fits the structure of the data with the least ceremony.
  2. Require a measured reason to go binary. "Throughput", "size", "speed" need a profile and a budget, not vibes. Often the text version is good enough by orders of magnitude.
  3. If you must use binary, build a text twin. A --dump or --inspect mode that emits the equivalent text representation. Never ship a format you can't print.
  4. Make textual formats line-oriented when you can. One record per line means standard tools (grep, awk, cut, sort, uniq, head, tail) just work — for free, forever.
  5. Be conservative about format choice. Cute custom syntax is a forever cost; existing standards (JSON, INI, RFC-822) are free leverage.

Red flags (rationalizations to reject)

  • "Text is too slow / too big." — Measure. For most workloads the gap is invisible; for the rest, compression is one pipe stage away.
  • "Nobody reads it by hand." — Until the day production breaks and you'd kill for the ability to.
  • "Binary is more typed/safer." — Type safety belongs in the parser, not the byte layout. A schema'd text format gives you both.

Composes with

  • [[rule-of-composition]] — text is what pipelines speak; binary breaks the chain.
  • [[rule-of-robustness]] — textual formats let you be liberal in what you accept and audit what you emit.
  • [[prove-dont-assume]] — text means you can actually see the bytes when something looks wrong, instead of trusting the marshaller.
  • [[dry-audit]] — a textual canonical format prevents the "code knows X, fixture knows Y, doc says Z" drift.

Read the full file on GitHub · 37 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. 12d ago First seen · 37 lines · 51 tokens per session scan A 2f2afabee35b

Subscribe to this mod's changes

rule-of-textuality is a skill published in the GitHub repository jonZlotnik/how-to-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 593 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

agui-dotnet-protobuf

Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…

ag-ui-protocol/ag-ui · 162 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

fastapi-router-py

Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.

microsoft/skills · 46 tokens

aws-sdk-java-v2-core

Provides AWS SDK for Java 2.x client configuration, credential resolution, HTTP client tuning, timeout, retry, and testing patterns. Use when creating or hardening AWS service clients, wiring Spring Boot beans, debugging auth or region issues, or choosing sync vs async SDK usage.

giuseppe-trisciuoglio/developer-kit · 62 tokens

migrate-segw-to-rap

Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…

arc-mcp/arc-1 · 106 tokens