presence-reset

presence-reset is a command for Claude Code from sara-star-quant/presence. It costs 25 tokens per session (834 once invoked), scanned A, original, Apache-2.0.

A command for deleting saved presence data at different scopes, such as the current project, event records, warnings, or all presence state. It asks for confirmation before deleting anything.

In plain words
What is it for?
Clearing project data, telemetry, events, warnings, encrypted state, or all files under the presence state directory.
Why use it?
It removes outdated or unwanted state while showing which paths will be deleted first.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the presence plugin — 3 skills, 7 commands, 1 agent shipped together

Good fit Clearing project data, telemetry, events, warnings, encrypted state, or all files under the presence state directory.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add sara-star-quant/presence
Claude Code
/plugin install presence

Made for: Claude Code.

Or install presence, the plugin that ships this one along with the rest of its 3 skills, 7 commands, 1 agent.

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 presence-reset

README.md
[![agentmods](https://agentmods.dev/badge/commands/sara-star-quant/presence/presence-reset/github.svg)](https://agentmods.dev/commands/sara-star-quant/presence/presence-reset)
Your own site
<a href="https://agentmods.dev/commands/sara-star-quant/presence/presence-reset"><img src="https://agentmods.dev/badge/commands/sara-star-quant/presence/presence-reset/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 presence-reset

Your own site · 80×15
<a href="https://agentmods.dev/commands/sara-star-quant/presence/presence-reset"><img src="https://agentmods.dev/badge/commands/sara-star-quant/presence/presence-reset.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 834 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 $0.00025 $0.00834
Opus 5 $0.00013 $0.00417
Sonnet 5 $0.00005 $0.00167
Haiku 4.5 $0.00003 $0.00083

Measured 9d ago against content hash 0c7f6404d197, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

presence-reset 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 9d 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.

commands/presence-reset.md · 98 lines

What it actually says

Parse $ARGUMENTS for one of these flags. If none given, ask the user via AskUserQuestion which scope they want.

Available scopes:

Flag Effect
--project Delete model.md and event log for the current repo only
--telemetry Delete claims/outcomes/confidence (all projects)
--events Delete event log for the current repo
--warnings Clear warnings.log and one-shot warning markers
--crypto Rotate the AES-GCM data key in the OS keychain AND wipe all encrypted state files (telemetry, events). Plain state files untouched.
--all Wipe everything under ~/.claude/presence/ (state only; plugin files untouched). Does NOT touch the keychain key.

Always confirm with the user before deleting via AskUserQuestion. Show them exactly what paths will be removed first.

For each scope, the operation is:

PRESENCE_ROOT="${CLAUDE_PLUGIN_ROOT:-$(realpath ~/.claude/plugins/presence 2>/dev/null || echo .)}"

# --project
PYTHONPATH="$PRESENCE_ROOT/lib" python3 -c "
from _common import project_dir, events_dir
import shutil, sys
for d in (project_dir('$PWD'), events_dir('$PWD')):
    if d.exists():
        shutil.rmtree(d)
        print(f'removed {d}')
"

# --telemetry
PYTHONPATH="$PRESENCE_ROOT/lib" python3 -c "
from _common import telemetry_dir
import shutil
d = telemetry_dir()
if d.exists():
    shutil.rmtree(d); print(f'removed {d}')
"

# --events
PYTHONPATH="$PRESENCE_ROOT/lib" python3 -c "
from _common import events_dir
import shutil
d = events_dir('$PWD')
if d.exists():
    shutil.rmtree(d); print(f'removed {d}')
"

# --warnings
PYTHONPATH="$PRESENCE_ROOT/lib" python3 -c "
from warnings_log import clear_warnings_state
from _common import reset_counter
clear_warnings_state()
reset_counter('warning'); reset_counter('error')
print('warnings cleared')
"

# --crypto (rotate key + wipe encrypted state; user must confirm separately)
PYTHONPATH="$PRESENCE_ROOT/lib" python3 -c "
import shutil
from pathlib import Path
import crypto
from _common import telemetry_dir, events_dir, state_dir

# Wipe encrypted state files (telemetry/events). Plain state stays.
# We can't easily distinguish per-line which files are mixed, so we wipe both
# directories entirely. Caller has confirmed via AskUserQuestion.
for d in (telemetry_dir(), state_dir() / 'events'):
    if d.exists():
        shutil.rmtree(d)
        print(f'wiped: {d}')

# Rotate the data key (existing ciphertext, if any survived, becomes unreadable)
new_key = crypto.rotate_key()
if new_key:
    print('keychain data key rotated; existing encrypted state is unreadable from now on')
else:
    print('warning: could not rotate key (cryptography lib or keychain unavailable)')
"

# --all
PYTHONPATH="$PRESENCE_ROOT/lib" python3 -c "
from _common import state_dir
import shutil
d = state_dir()
if d.exists():
    shutil.rmtree(d); print(f'removed {d}')
"

The plugin install itself (under ~/.claude/plugins/presence/) is never touched by reset. Only the state directory.

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. 9d ago First seen · 98 lines · 25 tokens per session scan A 0c7f6404d197

Subscribe to this mod's changes

presence-reset is a command published in the GitHub repository sara-star-quant/presence (7 stars, last pushed 3d ago), licensed Apache-2.0. It adds 25 tokens to every session and 834 once invoked, about $0.0001 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 2026-08-31.