create-custom-tooling

A command that creates project-specific skills, commands, or hooks from repeated workflow patterns.

In plain words
What is it for?
Use it after an audit to generate reusable knowledge, slash commands, or automated tool-event actions for the project.
Why use it?
It turns recurring manual work into reusable tooling after a workflow audit identifies a pattern several times.

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/marcusgoll/spec-flow/create-custom-tooling
Clone the repo
git clone --depth 1 https://github.com/marcusgoll/Spec-Flow

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,615 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00021 $0.02615
Opus 5 $0.00010 $0.01307
Sonnet 5 $0.00004 $0.00523
Haiku 4.5 $0.00002 $0.00262

Measured 3d ago against content hash 18c95c7fdd98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

create-custom-tooling scanned grade C with 2 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Hooks: !`cat .claude/settings.json 2>/dev/null | grep -A5 '"hooks"' || echo "none"`

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

- Skills: !`ls .claude/skills/project-custom/ 2>/dev/null || echo "none"`
.claude/commands/meta/create-custom-tooling.md · 407 lines

How it starts

The opening of the file, as written. The whole thing — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/create-custom-tooling — Pattern-Based Tooling Generation

Purpose: Transform recurring code patterns detected during /audit-workflow into reusable project-specific skills, slash commands, or hooks.

Command: /create-custom-tooling [skill|command|hook] [pattern-name] [--from-audit <epic-slug>]

When to use:

  • After /audit-workflow identifies recurring patterns (3+ occurrences)
  • When you notice repetitive code structures across features
  • To codify project-specific conventions into reusable tools

Check for audit reports: !ls -la epics/*/audit-report.xml 2>/dev/null | head -5

Existing custom tooling:

  • Skills: !ls .claude/skills/project-custom/ 2>/dev/null || echo "none"
  • Commands: !ls .claude/commands/project-custom/ 2>/dev/null || echo "none"
  • Hooks: !cat .claude/settings.json 2>/dev/null | grep -A5 '"hooks"' || echo "none"

Tooling Types:

  • Skill: Reusable knowledge/templates that Claude loads on-demand (e.g., service boilerplate, CRUD patterns)
  • Command: Executable slash command for specific actions (e.g., /generate-crud, /create-migration)
  • Hook: Automated triggers on tool events (e.g., auto-format on file save, validate on commit)

Step 1: Parse Arguments and Determine Mode

Parse $ARGUMENTS:

const args = "$ARGUMENTS".trim().split(/\s+/);
const toolingType = args[0]; // skill, command, or hook
const patternName = args[1]; // e.g., "service-boilerplate"
const fromAuditFlag = args.includes('--from-audit');
const epicSlug = fromAuditFlag ? args[args.indexOf('--from-audit') + 1] : null;

If no arguments provided, enter discovery mode:

{
  "question": "What type of tooling do you want to create?",
  "header": "Tooling Type",
  "multiSelect": false,
  "options": [
    {"label": "Skill", "description": "Reusable knowledge/templates (e.g., service boilerplate)"},
    {"label": "Command", "description": "Executable slash command (e.g., /generate-crud)"},
    {"label": "Hook", "description": "Automated trigger on tool events (e.g., auto-lint)"}
  ]
}

Read the full file on GitHub · 407 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 · 407 lines · 0 tokens per session scan C 18c95c7fdd98

Subscribe to this mod's changes

create-custom-tooling is a command published in the GitHub repository marcusgoll/Spec-Flow (91 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 2,615 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.