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 agentmods add commands/missingpackage/nightshift/morninggit clone --depth 1 https://github.com/MissingPackage/nightshiftWhat 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 | $0.00019 | $0.00444 |
| Opus 5 | $0.00010 | $0.00222 |
| Sonnet 5 | $0.00004 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
morning 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
Assemble the AGGREGATED morning report across all projects (ruling C10, 2026-08-12: runs scheduled via tools/install-schedules.sh, no longer a ritual the user invokes — they read it from the app over breakfast). Write the report itself in the user's own language — user surface, "match the user's language" rule; only these instructions are English. Plain language: every project term explained in half a line or omitted; items and phases cited by TITLE, never the bare ID. Read-only: decisions remain his. Order:
- Trajectories. For every project under ~/Projects with active
.harness/goals/(skip goals withSTATUS: PAUSED): ONE line per goal — objective, distance now vs yesterday, what moves it next. Numbers from the tail ofdigests.md, not reconstructed. - The night. The digests.md entries after the last report: what the autonomous work produced, 2-3 lines per goal, most recent last. Loops dead or revived by the watchdog (~/.claude/loop-watchdog.log): say it first, it is the first thing he wants to know.
- Open decisions, frontier format. All pending decisions cross-project in ONE batch: numbered, one idea per question, ordered by importance, each with options and a recommended answer + cost of not deciding. Partial answers are the norm; he replies in chat, the agent transcribes into the record (docket). Never more than ~6: the rest wait for the next round, mention them only as a count.
- One line of health. Active timers, HANDOFF over 80 lines, silent hooks — only if there is something to say.
Total output ≤ 40 lines. If the night produced nothing and there are no decisions: say so in 3 lines and close — a long empty report is worse than no report.
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 First seen · 29 lines · 19 tokens per session scan A bd7ae6f9591a
morning is a command published in the GitHub repository MissingPackage/nightshift (2 stars, last pushed 15d ago), licensed MIT. It adds 19 tokens to every session and 444 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
research
Research a technical or product question.
safe-build
Build the application for development or production.
update
Use when: search results seem noisy, after bulk imports, or for periodic memory/registry maintenance.
plan-workflow
Generate a skill chain plan for a high-level goal by analyzing the skills registry for input/output compatibility.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
lrn
Execute the /vibeguard:learn command. $ARGUMENTS.