Borrowing it
Nothing to install: this file belongs to basher83/agent-auditor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/basher83/agent-auditor/main/.claude/commands/convert-to-slash.mdgit 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-slash)<a href="https://agentmods.dev/commands/basher83/agent-auditor/convert-to-slash"><img src="https://agentmods.dev/badge/commands/basher83/agent-auditor/convert-to-slash.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 5.1 | $0.00011 | $0.01565 |
| Opus 5 | $0.00005 | $0.00783 |
| Sonnet 5 | $0.00002 | $0.00313 |
| Haiku 4.5 | $0.00001 | $0.00156 |
Grade A, and why
convert-to-slash 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 6d 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-slash — 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Convert Sub-Agent to Slash Command
You are tasked with converting a sub-agent definition back to a slash command. This conversion should happen when parallelization or context isolation is no longer needed.
Input
You will receive a file path to a sub-agent file via $ARGUMENTS.
Decision Criteria - MUST VALIDATE FIRST
Before converting, you MUST validate that conversion is appropriate. A sub-agent should become a slash command when:
Convert when:
- ✅ No parallelization needed - Task runs once, not in parallel batches
- ✅ Context isolation not required - Results can stay in main conversation
- ✅ Simple repeatable action - One-off or simple recurring task
- ✅ Sequential operation - Not part of batch/parallel workflow
- ✅ Realized it was over-engineered - Fell into the "converting all commands to agents" anti-pattern
Do NOT convert when:
- ❌ Parallelization is still needed - Multiple instances running simultaneously
- ❌ Context isolation is required - Need to protect main context window
- ❌ Batch operations at scale - Processing multiple items in parallel
- ❌ Complex multi-step workflows - Might actually need a skill instead
Recovery Strategy
This command helps recover from the anti-pattern of converting all slash commands to sub-agents. 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. Many tasks work better as simple slash commands.
Conversion Process
Step 1: Read the sub-agent file
Read the file at $ARGUMENTS
Step 2: Analyze and validate
Ask the user these questions to validate conversion is appropriate:
- Do you no longer need parallelization (running multiple instances)?
- Do you no longer need context isolation (results can stay in main conversation)?
- Is this actually a simple repeatable task (not complex orchestration)?
- Would this work better as a slash command?
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.
- 6d ago First seen · 220 lines · 11 tokens per session scan A 52f26dbf7c8d
convert-to-slash is a command published in the GitHub repository basher83/agent-auditor (5 stars, last pushed 6mo ago), licensed MIT. It adds 11 tokens to every session and 1,565 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-slash, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.