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.
npx skills add Lifecycle-Innovations-Limited/claude-ops --skill tonightgit clone --depth 1 https://github.com/Lifecycle-Innovations-Limited/claude-opsWrote 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/lifecycle-innovations-limited/claude-ops/tonight)<a href="https://agentmods.dev/skills/lifecycle-innovations-limited/claude-ops/tonight"><img src="https://agentmods.dev/badge/skills/lifecycle-innovations-limited/claude-ops/tonight/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/skills/lifecycle-innovations-limited/claude-ops/tonight"><img src="https://agentmods.dev/badge/skills/lifecycle-innovations-limited/claude-ops/tonight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00029 | $0.00506 |
| Opus 5 | $0.00015 | $0.00253 |
| Sonnet 5 | $0.00006 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
tonight 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 2d 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
/ops:tonight
Load ops-rules before acting. Public repo (no personal data). Outbound: one draft → one approval → one send. If AskUserQuestion / Workflow are missing, follow Rule 10 in ops-rules (Hermes: numbered options / two-turn Telegram card; delegate_task).
The "before-bed brief." Counterpart to /ops:go (morning).
Output sections
- Tomorrow's calendar — every meeting >=15min with: attendees, prep status (brief
exists Y/N), and the suggested 1-line prep ask if no brief exists. Query every
calendar store (Google
--alland Notion show/calendar/appointments databases when Notion is configured). A miss on Google Calendar is not "nothing tomorrow." - Birthdays / anniversaries tomorrow — from Notion People DB. Pre-drafted message ready to send.
- Overdue outreach — anyone whose
next_nudge_due <= tomorrow. Top 3 only. - Top 3 priorities for tomorrow — pulled from Linear (assignee=me, priority<=High, updated last 7d, not Done).
- Unresolved from today — ledger entries with
status=awaiting_samstill open.
Behavior
- Runs in claude-ops when owner is at the Mac
- Runs in Perplexity when owner isn't (Perplexity reads the same Notion ledger)
- Both systems write a ledger entry
kind=nudge,brand=OPS,claim_key=tonight:YYYY-MM-DDso they don't both fire - Push notification only if section 5 has unresolved items OR section 3 has anyone past cadence
Schedule
Suggested cron: 30 21 * * 1-5 in your own time zone (9:30pm weekdays)
Or run manually with /ops:tonight
Ledger writes
Each section that surfaces an item writes a sub-entry so morning /ops:go can pick
up where this left off without re-deriving.
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.
- 2d ago Changed 351d419583ba
- 9d ago First seen · 47 lines · 29 tokens per session scan A 086dffb7af67
tonight is a skill published in the GitHub repository Lifecycle-Innovations-Limited/claude-ops (189 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 506 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 2026-09-03.
Other skills, from other repositories
change-management-planner
Plans organizational change initiatives including technology rollouts, process redesigns, and team restructuring. Maps stakeholders, identifies resistance, designs communication plans, and builds adoption strategies with measurable milestones.
employee-onboarding-designer
Designs structured employee onboarding programs that reduce time-to-productivity and improve retention. Creates day-by-day onboarding plans, training checklists, milestone assessments, and 30/60/90 day success criteria tailored to the role type.
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…
promote-idea
Converts an album idea from IDEAS.md into an actual album project in one step. Use when the user says "promote [idea title]", "turn idea into album", or "start working on [idea]".
work-unit-decomposition
Decompose implementation plans into discrete work units with enumerated DoD items, file scope declarations, dependency mapping, and human checkpoint flags.
anti-drift
Hierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specialization enforcement, and short task cycles.