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.
npx agentmods add commands/basher83/agent-auditor/convert-to-agentgit clone --depth 1 https://github.com/basher83/agent-auditorWrote 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.
[](https://agentmods.dev/commands/basher83/agent-auditor/convert-to-agent)<a href="https://agentmods.dev/commands/basher83/agent-auditor/convert-to-agent"><img src="https://agentmods.dev/badge/commands/basher83/agent-auditor/convert-to-agent.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00012 | $0.01735 |
| Opus 5 | $0.00006 | $0.00868 |
| Sonnet 5 | $0.00002 | $0.00347 |
| Haiku 4.5 | $0.00001 | $0.00173 |
Grade A, and why
convert-to-agent 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.
This is a copy
100% identical to convert-to-agent — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Convert Slash Command to Sub-Agent
You are tasked with converting a slash command to a sub-agent definition. This conversion should ONLY happen when appropriate based on the decision criteria.
Input
You will receive a file path to a slash command file via $ARGUMENTS.
Decision Criteria - MUST VALIDATE FIRST
Before converting, you MUST validate that conversion is appropriate. A slash command should become a sub-agent ONLY when:
Convert when:
- ✅ Parallelization is needed - "Whenever you see parallel, you should always just think sub-agents"
- ✅ Context isolation is required - You want to protect the main context window
- ✅ Scale/batch operations - Running the same task multiple times in parallel
- ✅ You're okay losing context afterward - Sub-agent context doesn't persist (unless resumable)
Do NOT convert when:
- ❌ One-off task - Keep as slash command
- ❌ Context matters later - Use main conversation instead
- ❌ Sequential operations - Keep as slash command or consider skill
- ❌ Simple repeatable actions - Keep as slash command
Critical Anti-Pattern Warning
From official guidance:
"There are a lot of engineers right now that are going all in on skills. They're converting all their slash commands to skills. I think that's a huge mistake."
The same applies to sub-agents. Do not convert slash commands to sub-agents unless there's a clear need for parallelization or context isolation.
Conversion Process
Step 1: Read the slash command file
Read the file at $ARGUMENTS
Step 2: Orchestrator Detection (Check FIRST)
Immediately after reading the file, analyze the content to detect if this is an orchestrator:
Check frontmatter:
- Does
allowed-toolsfield containTask?
Check body content for these keywords:
- "Task tool"
- "subagent" / "sub-agent"
- "spawn"
- "parallel agent"
- "multiple Task tool"
- "launch all subagents"
- "orchestrate"
If ANY orchestrator indicator is found:
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 · 237 lines · 12 tokens per session scan A c9cdd5d4fd58
convert-to-agent is a command published in the GitHub repository basher83/agent-auditor (5 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 1,735 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to convert-to-agent, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.