slash-command-finder

slash-command-finder is an agent for Claude Code from gpt-cmdr/ras-commander. It costs 48 tokens per session (934 once invoked), scanned A, original, MIT.

An assistant that finds repeated patterns in user prompts that could become slash commands. Slash commands are short typed shortcuts for common tasks.

In plain words
What is it for?
Use it to review conversation history for patterns such as building, testing, reviewing code, fixing bugs, planning, brainstorming, or committing changes.
Why use it?
It helps turn recurring requests into reusable commands, so developers do not have to repeat the same instructions manually.

Agent 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 agents/gpt-cmdr/ras-commander/slash-command-finder
Clone the repo
git clone --depth 1 https://github.com/gpt-cmdr/ras-commander

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.

agentmods badge for slash-command-finder

README.md
[![agentmods](https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/slash-command-finder.svg)](https://agentmods.dev/agents/gpt-cmdr/ras-commander/slash-command-finder)
Your own site
<a href="https://agentmods.dev/agents/gpt-cmdr/ras-commander/slash-command-finder"><img src="https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/slash-command-finder.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 934 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 5.1 $0.00048 $0.00934
Opus 5 $0.00024 $0.00467
Sonnet 5 $0.00010 $0.00187
Haiku 4.5 $0.00005 $0.00093

Measured 5d ago against content hash a73e11dbee4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

slash-command-finder 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 5d 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/agents/slash-command-finder.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Slash Command Finder

Identify repetitive user prompts suitable for slash command automation.

Purpose

Analyze user prompts to detect:

  • Frequently repeated phrases
  • Common command patterns
  • Workflow triggers
  • Automation opportunities

Known Patterns

Detect these pre-configured patterns:

Pattern Regex Suggested Command
ultrathink \bultrathink\b /ultrathink
deep research \bdeep\s*research\b /deep-research
run build \b(run|execute)\s+(the\s+)?build\b /build
run tests \b(run|execute)\s+(the\s+)?(tests?|test\s*suite)\b /test
commit \b(commit|create\s+a?\s*commit)\b.*changes? /commit
plan mode \b(enter\s+)?plan\s*mode\b /plan
brainstorm \bbrainstorm\b /brainstorm
review \breview\s+(the\s+)?(code|changes|pr)\b /review
explain \bexplain\s+(this|the|how)\b /explain
fix \bfix\s+(this|the|all)\s*(error|bug|issue)s?\b /fix
refactor \brefactor\b /refactor

Analysis Method

1. Pattern Matching

import re
from collections import Counter

pattern_counts = Counter()
for prompt in prompts:
    for name, regex in KNOWN_PATTERNS.items():
        if re.search(regex, prompt, re.IGNORECASE):
            pattern_counts[name] += 1

2. N-Gram Analysis

# Find frequent 2-5 word phrases
for n in range(2, 6):
    for i in range(len(words) - n + 1):
        ngram = " ".join(words[i:i+n])
        if len(ngram) > 10:
            ngram_counts[ngram] += 1

3. Action Verb Detection

action_verbs = {"create", "add", "remove", "delete", "update",
                "run", "execute", "check", "fix", "generate"}

for prompt in prompts:
    first_verb = extract_first_verb(prompt)
    if first_verb in action_verbs:
        verb_phrases[first_verb + " " + next_words] += 1

Output Format

{
  "candidates": [
    {
      "command_name": "/ultrathink",
      "trigger_phrases": ["ultrathink and", "ultrathink about"],
      "frequency": 87,
      "priority": "high",
      "category": "workflow",
      "suggested_implementation": "Enable extended thinking mode",
      "example_uses": ["ultrathink and create a plan...", ...]
    }
  ]
}

Read the full file on GitHub · 132 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. 5d ago First seen · 132 lines · 48 tokens per session scan A a73e11dbee4b

Subscribe to this mod's changes

slash-command-finder is an agent published in the GitHub repository gpt-cmdr/ras-commander (79 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 934 once invoked, about $0.0002 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.