A set of command-design rules for a knowledge system, where each command represents one complete user workflow.

Use it to design commands for creating, drafting, reviewing, or exporting content, with separate files and declared context.

It prevents commands from mixing unrelated jobs and makes it clear which context and specialist agents each workflow needs.

README — Command for Claude Code by davidmatousek: A set of command-design rules for a knowledge system…

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 commands/davidmatousek/tachi/readme

Clone the repo

git clone --depth 1 https://github.com/davidmatousek/tachi

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/davidmatousek/tachi/readme.svg)](https://agentmods.dev/commands/davidmatousek/tachi/readme)

Your own site

<a href="https://agentmods.dev/commands/davidmatousek/tachi/readme"><img src="https://agentmods.dev/badge/commands/davidmatousek/tachi/readme.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 413 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00413
Opus 5	$0.00000	$0.00206
Sonnet 5	$0.00000	$0.00083
Haiku 4.5	$0.00000	$0.00041

Measured 4d ago against content hash 13c355ecd2fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

README 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.

.claude/commands/README.md · 40 lines

What it actually says

Commands — Knowledge System Orchestration

Pattern: Command-per-Workflow

Each user workflow maps to one command. A command orchestrates one complete user-facing operation — it is the unit of user intent.

Rule: One command = one workflow = one user intent.

How to Design Commands

List your workflows — What does a user do with your knowledge system? Common workflows include creating new outputs, drafting content, reviewing quality, and exporting for delivery.
One command per workflow — Each workflow gets its own command file in this directory. Name files in kebab-case (e.g., draft-resume.md, review-chapter.md).
Define context loading — Each command declares which content it needs from _Config/ContextLoading.yaml. Never load everything; load only what the workflow requires.
Map to agents — Each command may invoke one or more agent personas from .claude/agents/. The command orchestrates; agents execute.

Example Structure

commands/
  new-output.md       # Initialize from master content
  draft.md            # Generate using voice + style + context
  review.md           # Evaluate against scoring rubric
  export.md           # Format for delivery

Anti-Patterns

Monolithic command: A single command that handles analysis, drafting, scoring, and export. Decompose into focused commands instead.
Technical-operation commands: Commands like /load-context or /validate-yaml expose internals. Technical operations belong inside command implementations, not as user-facing commands.
AOD command duplication: Never create product commands that replicate /aod.define, /aod.spec, etc. AOD commands build the system; product commands operate it.

References

Command-per-workflow pattern: STACK.md → Architecture Pattern
Context loading configuration: _Config/ContextLoading.yaml
Agent persona mapping: .claude/agents/README.md

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.

4d ago First seen · 40 lines · 0 tokens per session scan A 13c355ecd2fe

Subscribe to this mod's changes

README is a command published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 21d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 413 tokens. 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.

Productivity Writing and docs agentic-security ai-security attack-trees claude-code cybersecurity devsecops

README