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.
/plugin marketplace add sara-star-quant/presence/plugin install presenceWrote 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/sara-star-quant/presence/presence-reset)<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.
<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>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 | $0.00025 | $0.00834 |
| Opus 5 | $0.00013 | $0.00417 |
| Sonnet 5 | $0.00005 | $0.00167 |
| Haiku 4.5 | $0.00003 | $0.00083 |
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.
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.
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.
- 9d ago First seen · 98 lines · 25 tokens per session scan A 0c7f6404d197
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.
Other commands, from other repositories
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
show
Show this project's saved Recall context (.recall/context.md).
evolve-lite-adapt-memory
Mirror a just-saved native memory into the shared evolve store so it becomes shareable and auditable.
patterns
Scan recent sessions for recurring patterns and turn them into captures (rules, concept notes, writing seeds).
ccc-context-budget
Visual context window budget analyzer — shows usage gauge, identifies bloat sources, recommends when to save session and compact.
pin
Break checkpoint — status display, session log, optional MEMORY.md update.