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 orwa-mahmoud/nightshift/plugin install nightshiftWrote 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/skills/orwa-mahmoud/nightshift/stop)<a href="https://agentmods.dev/skills/orwa-mahmoud/nightshift/stop"><img src="https://agentmods.dev/badge/skills/orwa-mahmoud/nightshift/stop.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.00839 |
| Opus 5 | $0.00009 | $0.00419 |
| Sonnet 5 | $0.00004 | $0.00168 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
stop 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 yesterday.
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
Pause the host-opened project immediately so the owner can edit the punch list and resume later.
Bind once, then never search, guess, or re-resolve. $TASK_ROOT is the host-opened project
folder: ${CLAUDE_PROJECT_DIR} on Claude Code; on Codex the CODEX_PROJECT_DIR recovery override
when Nightshift set it, otherwise pwd -P captured before any other shell call.
$NIGHTSHIFT_WORKSPACE is the validated absolute target of $TASK_ROOT/.nightshift-link when that
link exists, otherwise $TASK_ROOT. Then NS="$NIGHTSHIFT_WORKSPACE/.nightshift" (native Windows:
$NS = Join-Path $NIGHTSHIFT_WORKSPACE '.nightshift'), and every Nightshift file is $NS/<name>
for the rest of the run; helpers taking --project or -Project receive
"$NIGHTSHIFT_WORKSPACE". The shell's working directory persists between calls, so a bare path is
never safe.
Resolve the installed plugin root to an absolute $NIGHTSHIFT_PLUGIN_ROOT: use
${CLAUDE_PLUGIN_ROOT} on Claude Code; on Codex use $PLUGIN_ROOT when available, otherwise derive
it from the absolute path attached to this skill (skills/stop/SKILL.md). Substitute that
absolute path below; never search for the plugin.
On native Windows, use the PowerShell tool and native paths throughout. Resolve the same values
from $env:CLAUDE_PROJECT_DIR, $env:CODEX_PROJECT_DIR, and $env:PLUGIN_ROOT, with
[Environment]::CurrentDirectory as the Codex cwd fallback. Do not route Stop through WSL or Git
Bash.
Run the trusted helper. Do not write $NS/STOP by hand, do not delete $NS/.shift-armed, and do
not kill $NS/.watchman yourself — the helper performs the safe teardown:
"$NIGHTSHIFT_PLUGIN_ROOT/runtime/stop-shift.sh" --project "$NIGHTSHIFT_WORKSPACE"
On native Windows:
& "$NIGHTSHIFT_PLUGIN_ROOT\runtime\windows\stop-shift.ps1" -Project "$NIGHTSHIFT_WORKSPACE"
The helper writes $NS/STOP with a reason and UTC timestamp, appends stopped by owner to
$NS/shift-log.md, and kills only a verified live Nightshift watchman. It does not remove
$NS/.shift-armed. Open boxes stay open as the record. Hardhat stays until clock-out writes
$NS/.ended. Reset is the manual escape. The deadline, punch list, rules, parking lot, work
orders, receipts, archives, research, opportunities, and shift history stay on disk. Do not wait
for a later Stop event to write the marker — the helper writes it now.
Report the helper's open-items count and that the deadline was preserved. A second Stop is safe.
Resume later with Start (/nightshift:start on Claude Code, or ask Nightshift to start on Codex).
Start clears the pause markers and begins a new ownership lease. A future preserved deadline
remains the deadline. An expired preserved deadline is not silently renewed: write a new UNIX epoch
to $NS/deadline, or run Reset then Start.
This works from the bound conversation, from a helper conversation, and when a failed clock-out left a recovery nonce that still fences the recorded conversation.
Panic form (does not disarm immediately): from any POSIX terminal,
touch "$NS/STOP". In native Windows PowerShell, run
New-Item -ItemType File -Force "$NS\STOP". That marker is honored at the next Stop event or
watchman wake. Prefer the helper when the model is stuck — it does not wait for that event.
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.
- yesterday Changed · -4 lines 73ff677e640a
- 7d ago First seen · 65 lines · 18 tokens per session scan A 67e2086e7560
stop is a skill published in the GitHub repository orwa-mahmoud/nightshift (52 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 839 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 2026-08-30.
Other skills, from other repositories
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
article-writer
Multi-style article creation skill. Supports 5 writing styles (deep analysis, practical guide, story-driven, opinion, news brief), including complete workflow: material collection → outline → content → formatting. Activated when users mention "write article", "write post", "create", or "draft".
skin-creator
Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.
weather
Get current weather and forecasts (no API key required).
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.