contribute-a-command

A command for adding a new slash command to this repository. It creates the command's source file using the repository's required structure and shared guidelines.

In plain words
What is it for?
Use it when contributing a custom command, including its name, arguments, shared content, and command-specific instructions. It is intended for this repository's command sources.
Why use it?
It removes the need to remember the project's file layout and command-format rules. This helps new commands fit the existing collection consistently.

Command for Claude Code

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/wbern/agent-instructions/contribute-a-command
Clone the repo
git clone --depth 1 https://github.com/wbern/agent-instructions

Made for: Claude Code.

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,547 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.

ModelPer sessionOnce invoked
Fable 5 $0.00008 $0.01547
Opus 5 $0.00004 $0.00773
Sonnet 5 $0.00002 $0.00309
Haiku 4.5 $0.00001 $0.00155

Measured 2d ago against content hash 0a3a2ddeb5dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

contribute-a-command 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 2d 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/contribute-a-command.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

General Guidelines

Output Style

  • Never explicitly mention TDD in code, comments, commits, PRs, or issues
  • Write natural, descriptive code without meta-commentary about the development process
  • The code should speak for itself - TDD is the process, not the product

Beads is available for task tracking. Use mcp__beads__* tools to manage issues (the user interacts via bd commands).

Plan File Restriction

NEVER create, read, or update plan.md files. Claude Code's internal planning files are disabled for this project. Use other methods to track implementation progress (e.g., comments, todo lists, or external tools).

Create a new custom command in src/sources/ following the patterns below. Assess the structure carefully using the below info but also researching the repo.

User arguments:

Contribute-a-command: $ARGUMENTS

End of user arguments

File Structure

Create src/sources/<command-name>.md with:

  1. Frontmatter (required fields below)
  2. INCLUDE directives for shared content
  • We always include the docs INCLUDE path='src/fragments/universal-guidelines.md' fragment
  1. Command-specific content
  2. Exactly ONE [DOLLAR]ARGUMENTS placeholder

After creating, run pnpm build and pnpm vitest run -u to update snapshots.

Frontmatter Template

---
description: Brief description for /help
argument-hint: [optional-arg] or <required-arg> or (no arguments - interactive)
_hint: Short 2-3 word hint
_category: Test-Driven Development | Planning | Workflow | Ship / Show / Ask | Utilities | [Something else]
_order: 1-99
---

Optional: _requested-tools (array), _selectedByDefault: false

Category Patterns

Test-Driven Development (spike, red, green, refactor, cycle)

**User arguments:**

[CommandName]: [DOLLAR]ARGUMENTS

**End of user arguments**

[PHASE] PHASE! Apply the below to the user input above.

< !-- docs INCLUDE path='src/fragments/universal-guidelines.md' -->
< !-- /docs -->

< !-- docs INCLUDE path='src/fragments/beads-awareness.md' featureFlag='beads' -->
< !-- /docs -->

< !-- docs INCLUDE path='src/fragments/fallback-arguments-beads.md' featureFlag='beads' elsePath='src/fragments/fallback-arguments.md' -->
< !-- /docs -->

< !-- docs INCLUDE path='src/fragments/tdd-fundamentals.md' -->
< !-- /docs -->

Read the full file on GitHub · 186 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. 2d ago First seen · 186 lines · 8 tokens per session scan A 0a3a2ddeb5dd

Subscribe to this mod's changes

contribute-a-command is a command published in the GitHub repository wbern/agent-instructions (168 stars, last pushed 3mo ago), licensed MIT. It adds 8 tokens to every session and 1,547 once invoked, about $0.0000 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.