auto-clear

auto-clear is a command for Claude Code from shwilliamson/automatasaurus. It costs 0 tokens per session (841 once invoked), scanned A, original, MIT.

A command for finding and removing generated planning and context files from a project. These can include discovery notes, implementation plans, design documents, and agent project files.

In plain words
What is it for?
Use it to locate generated planning files, review what would be removed, and clear them when restarting project planning.
Why use it?
It helps start planning again with a clean set of generated documents and shows which files are candidates for removal before cleanup.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths.

Good fit Use it to locate generated planning files, review what would be removed, and clear them when restarting project planning.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/shwilliamson/automatasaurus/auto-clear
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.

Clone the repo
git clone --depth 1 https://github.com/shwilliamson/automatasaurus

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 auto-clear

README.md
[![agentmods](https://agentmods.dev/badge/commands/shwilliamson/automatasaurus/auto-clear/github.svg)](https://agentmods.dev/commands/shwilliamson/automatasaurus/auto-clear)
Your own site
<a href="https://agentmods.dev/commands/shwilliamson/automatasaurus/auto-clear"><img src="https://agentmods.dev/badge/commands/shwilliamson/automatasaurus/auto-clear/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 auto-clear

Your own site · 80×15
<a href="https://agentmods.dev/commands/shwilliamson/automatasaurus/auto-clear"><img src="https://agentmods.dev/badge/commands/shwilliamson/automatasaurus/auto-clear.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 841 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00841
Opus 5.5 $0.00000 $0.00336
Sonnet 5.5 $0.00000 $0.00168
Haiku 4.5 $0.00000 $0.00084

Measured 2mo ago against content hash 9396d01b657c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auto-clear 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 2mo 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.

template/commands/auto-clear.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clear - Remove Generated Planning Files

Remove all generated planning and context files to start fresh.

Workflow Mode

WORKFLOW_MODE: clear

Instructions

You are the Cleanup Assistant. Your job is to:

  1. Find all generated planning files
  2. Show the user what will be removed
  3. Offer backup or direct deletion
  4. Clean up and confirm

Phase 1: Find Generated Files

Glob for all generated planning and context files:

# Discovery files
ls discovery.md discovery-*.md 2>/dev/null

# Implementation plan files
ls implementation-plan.md implementation-plan-*.md 2>/dev/null

# Design system
ls design-system.md 2>/dev/null

# Agent PROJECT.md files
ls .claude/agents/*/PROJECT.md 2>/dev/null

If no files are found, inform the user:

No generated planning files found. Nothing to clear.

Phase 2: Present Files to User

List all found files with sizes:

## Generated Planning Files Found

| File | Size |
|------|------|
| discovery.md | X KB |
| discovery-2.md | X KB |
| implementation-plan.md | X KB |
| design-system.md | X KB |
| .claude/agents/developer/PROJECT.md | X KB |
| .claude/agents/architect/PROJECT.md | X KB |
| .claude/agents/designer/PROJECT.md | X KB |
| .claude/agents/tester/PROJECT.md | X KB |

What would you like to do?
1. **Delete all** - Remove all generated files
2. **Backup then delete** - Copy to `.automatasaurus/backups/` first, then remove
3. **Cancel** - Keep everything

Phase 3: Execute Chosen Action

Option 1: Delete All

rm -f discovery.md discovery-*.md
rm -f implementation-plan.md implementation-plan-*.md
rm -f design-system.md
rm -f .claude/agents/*/PROJECT.md

Option 2: Backup Then Delete

# Create timestamped backup directory
BACKUP_DIR=".automatasaurus/backups/planning-$(date +%Y%m%d-%H%M%S)"
mkdir -p "$BACKUP_DIR"

# Copy all generated files preserving structure
cp discovery.md discovery-*.md "$BACKUP_DIR/" 2>/dev/null
cp implementation-plan.md implementation-plan-*.md "$BACKUP_DIR/" 2>/dev/null
cp design-system.md "$BACKUP_DIR/" 2>/dev/null
mkdir -p "$BACKUP_DIR/agents"
for agent_dir in .claude/agents/*/; do
  agent_name=$(basename "$agent_dir")
  if [ -f "$agent_dir/PROJECT.md" ]; then
    mkdir -p "$BACKUP_DIR/agents/$agent_name"
    cp "$agent_dir/PROJECT.md" "$BACKUP_DIR/agents/$agent_name/"
  fi
done

# Then delete
rm -f discovery.md discovery-*.md
rm -f implementation-plan.md implementation-plan-*.md
rm -f design-system.md
rm -f .claude/agents/*/PROJECT.md

Read the full file on GitHub · 150 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. 2mo ago First seen · 150 lines · 0 tokens per session scan A 9396d01b657c

Subscribe to this mod's changes

auto-clear is a command published in the GitHub repository shwilliamson/automatasaurus (5 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 841 tokens. 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 2026-08-31.

Related

auto-clear compared with commands from other repositories

auto-clear next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
auto-clearshwilliamson/automatasaurusCommand58mo agoMITA0Claude Code
minutes-ideassilverstein/minutesCommand1.6kyesterdayMITA48Claude Code, OpenCode
learnReflexioAI/claude-smartCommand7913d agoApache-2.0A14Claude Code
memory-storeverygoodplugins/mcp-automemCommand66yesterdayMITA10Claude Code
analyze-contextRohiRIK/OpenLtmCommand298d agoMITA39Claude Code
cc-memoryTheLobbi/claudeCommand217d agoMITA0Claude Code
lians-recallLians-ai/LiansCommand175d agoApache-2.0A19Claude Code