fully-automated-prompt-optimization: Command for Claude Code

.claude/commands/reset-tenant.md

reset-tenant is a command for Claude Code from cisco-foundation-ai/fully-automated-prompt-optimization. It costs 0 tokens per session (1,705 once invoked), scanned C, original, Apache-2.0.

A command that returns a tenant to its original baseline setup. A tenant is a separate directory or account whose prompts and optimization history are managed independently.

In plain words
What is it for?
Use it to undo prompt-optimization work for a named tenant, clear its optimization artifacts, and restore the baseline prompt state.
Why use it?
It removes prompt variants, chain variants, iteration memory, and optimization log entries when you need a clean starting point. The changes remain available in Git history.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is cisco-foundation-ai/fully-automated-prompt-optimization's own configuration. It tells Claude Code how to work on fully-automated-prompt-optimization itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fully-automated-prompt-optimization configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cisco-foundation-ai/fully-automated-prompt-optimization. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cisco-foundation-ai/fully-automated-prompt-optimization/main/.claude/commands/reset-tenant.md
Clone the repo
git clone --depth 1 https://github.com/cisco-foundation-ai/fully-automated-prompt-optimization

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 reset-tenant

README.md
[![agentmods](https://agentmods.dev/badge/commands/cisco-foundation-ai/fully-automated-prompt-optimization/reset-tenant/github.svg)](https://agentmods.dev/commands/cisco-foundation-ai/fully-automated-prompt-optimization/reset-tenant)
Your own site
<a href="https://agentmods.dev/commands/cisco-foundation-ai/fully-automated-prompt-optimization/reset-tenant"><img src="https://agentmods.dev/badge/commands/cisco-foundation-ai/fully-automated-prompt-optimization/reset-tenant/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for reset-tenant

Your own site · 80×15
<a href="https://agentmods.dev/commands/cisco-foundation-ai/fully-automated-prompt-optimization/reset-tenant"><img src="https://agentmods.dev/badge/commands/cisco-foundation-ai/fully-automated-prompt-optimization/reset-tenant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,705 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.01705
Opus 5 $0.00000 $0.00852
Sonnet 5 $0.00000 $0.00341
Haiku 4.5 $0.00000 $0.00170

Measured 12d ago against content hash a3049961ebcf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

reset-tenant scanned grade C with 1 finding 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 12d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

Remove contents of these directories if they exist (these are gitignored, use `rm -rf`):
.claude/commands/reset-tenant.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.


description: > Reset a tenant to baseline (variant-001), removing all optimization artifacts. TRIGGER when: user wants to reset a tenant, start fresh, clear optimization history, revert to baseline, undo all prompt iterations, or clean-slate a tenant. DO NOT TRIGGER when: user wants to run evals (use eval-runner), optimize prompts (use optimization agent), or create synthetic data (use synthetic-samples).

Reset Tenant to Baseline

Overview

Remove all optimization artifacts (non-baseline prompt variants, chain variants, iteration memory, optimization changelog entries) from a tenant, leaving it in a clean baseline state as if no optimization had ever been performed. Git history preserves the work.

Inputs

  • tenant_id (required): The tenant directory name under tenants/. If not provided, ask the user.

Pre-flight

  1. Validate tenant exists: Confirm tenants/<tenant_id>/ exists. Abort if not.

  2. Detect prompt layout (per-tenant, not assumed globally):

    • Modules layout: tenants/<tenant_id>/prompts/modules/ exists and contains subdirectories with variant files (e.g. hotpotqa)
    • Flat layout: tenants/<tenant_id>/prompts/variants/ contains variant files directly (e.g. aime2025, cti_rcm)
    • If neither directory exists, warn and skip prompt variant cleanup.
  3. Inventory what will be reset — scan and list:

    • Non-baseline prompt variants (variant-002 and above) in whichever layout applies
    • Chain variant files in chains/variants/ (if directory exists)
    • Config files referencing non-baseline variants in configs/
    • Changelog entries in docs/change-log.md referencing variant-002 or higher
    • Iteration memory in docs/iteration-memory.jsonl (if it exists and is non-empty)
    • Local eval outputs in evals/tmp/ and reports/ (if they exist)
  4. Show the inventory to the user and ask for explicit confirmation before proceeding. If there is nothing to reset, report that the tenant is already at baseline and stop.

Read the full file on GitHub · 151 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. 12d ago First seen · 151 lines · 0 tokens per session scan C a3049961ebcf

Subscribe to this mod's changes

reset-tenant is a command published in the GitHub repository cisco-foundation-ai/fully-automated-prompt-optimization (107 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,705 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.