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-unlock)<a href="https://agentmods.dev/commands/sara-star-quant/presence/presence-unlock"><img src="https://agentmods.dev/badge/commands/sara-star-quant/presence/presence-unlock/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-unlock"><img src="https://agentmods.dev/badge/commands/sara-star-quant/presence/presence-unlock.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 | $0.00039 | $0.00403 |
| Opus 5 | $0.00019 | $0.00201 |
| Sonnet 5 | $0.00008 | $0.00081 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
presence-unlock 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 10d 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
Create an unlock marker so the next settings-modifying operation (preset switch via /presence-preset use, or any direct ~/.claude/presence/settings.json edit) is permitted under the zerotrust preset.
If $ARGUMENTS contains --ttl <seconds>, use that TTL; otherwise default 60 seconds.
PRESENCE_ROOT="${CLAUDE_PLUGIN_ROOT:-$(realpath ~/.claude/plugins/presence 2>/dev/null || echo .)}"
TTL=60
if [[ "$ARGUMENTS" =~ --ttl[[:space:]]+([0-9]+) ]]; then
TTL="${BASH_REMATCH[1]}"
fi
PYTHONPATH="$PRESENCE_ROOT/lib" python3 -c "
import unlock
expire = unlock.unlock(ttl_seconds=$TTL)
import time
print(f'unlocked: settings writes permitted for the next $TTL second(s) (until {time.strftime(\"%H:%M:%S\", time.localtime(expire))})')
"
After this command, the user has the unlock window to make settings changes. If they don't make changes within the window, the marker expires and immutability resumes automatically.
If the active preset is NOT zerotrust (or any preset that sets settings.immutable: true), this command runs but has no practical effect: settings are already writable.
Note: this is a tamper-resistance signal, not a security barrier. A user with filesystem access can always remove ~/.claude/presence/.unlocked directly. The unlock flow exists to make accidental settings changes during a sensitive session require an explicit conscious step.
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.
- 10d ago First seen · 30 lines · 39 tokens per session scan A d2359d143b01
presence-unlock is a command published in the GitHub repository sara-star-quant/presence (7 stars, last pushed 4d ago), licensed Apache-2.0. It adds 39 tokens to every session and 403 once invoked, about $0.0002 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
fable-eval
Run the fable-mode eval suite (probes → pairwise judge → report). Costs tokens — runs headless claude many times. Optional arg: a probe id substring to filter.
decree
Issue a decree. Seats the organization on first use, then dispatches the teams.
fable-status
Report fable-mode posture — output style, model/effort, hook telemetry drift counts.
report
The full account of the current decree — every figure verified before stated.
roster
Show the organization — roster, defect ledger, replacements, current cycle.
lore
Turn the lore on or off. Same organization, same rules — different register.