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 ZachBeta/claude-as-coach --skill daily-morning-routine-basegit clone --depth 1 https://github.com/ZachBeta/claude-as-coachWrote 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/zachbeta/claude-as-coach/daily-morning-routine-base)<a href="https://agentmods.dev/skills/zachbeta/claude-as-coach/daily-morning-routine-base"><img src="https://agentmods.dev/badge/skills/zachbeta/claude-as-coach/daily-morning-routine-base/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/zachbeta/claude-as-coach/daily-morning-routine-base"><img src="https://agentmods.dev/badge/skills/zachbeta/claude-as-coach/daily-morning-routine-base.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 | $0.00080 | $0.01703 |
| Opus 5.5 | $0.00032 | $0.00681 |
| Sonnet 5.5 | $0.00016 | $0.00341 |
| Haiku 4.5 | $0.00008 | $0.00170 |
Grade A, and why
daily-morning-routine-base 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Daily Morning Routine (Base Framework)
Process
1. Verify Current Date
CRITICAL FIRST STEP
TZ='America/New_York' date '+%A, %B %d, %Y - %I:%M %p %Z'
State clearly: "Today is [Day], [Full Date]."
2. Find Most Recent Summary
Look for pattern: Summary-YYYY-MM-DD-*.md or Summary-YYYY-MM-DD-Day-to-DD-Day-*.md in project files.
Note: Summaries may use range-based naming if they span calendar boundaries (e.g., Summary-2026-01-15-Thu-to-16-Fri-week-5-long-run.md).
Sort by date (newest first), use the most recent one.
If the most recent summary is from more than 1 day ago, note the gap.
3. Confirm with User
Found: Summary-2026-01-15-Thu-to-16-Fri-week-5-long-run.md
This is the most recent summary. Attend to it for morning brief?
Wait for confirmation.
4. Attend to Summary
DO NOT re-read with view - project documents already loaded in context.
Instead, "heat up the KV cache" by:
- Referencing specific filename from project_files
- Summarizing key content in detail
- Focusing attention through synthesis
Think: Document already in RAM, just heating cache lines for fast access.
5. Generate Morning Brief
Format: detail-first, TL;DR at bottom, threads at end
## Ground Truth
Today is [Day], [Full Date]
[Current training phase/week]
---
## Yesterday's Detail
### [Major Theme 1]
[Expanded context - 2-3 paragraphs]
### [Major Theme 2]
[Key patterns, decisions, insights]
---
## Yesterday's Snapshot (TL;DR)
- [Key number]
- [Major event]
- [What worked/didn't]
- [Evening state]
## Today's Focus (TL;DR)
- [Priority question]
- [What to track]
- [Training focus]
Structure: Detail sections first (heats cache on loaded content) → TL;DR at bottom (scannable).
User reads detail OR jumps to TL;DR depending on morning state.
6. Reopen Contemplation Threads
After generating the brief, do NOT close the conversation.
Pull from summary's "Tomorrow's Seeds" section:
---
## Threads Still Warm
[From summary's "Threads still warm" - contemplation topics, questions raised, decisions pending]
**From yesterday:** "[One thing from today" - the single insight or question that was sitting with the user]
---
What's present this morning?
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.
- 2mo ago First seen · 228 lines · 80 tokens per session scan A cceebbc4ca89
daily-morning-routine-base is a skill published in the GitHub repository ZachBeta/claude-as-coach (5 stars, last pushed 9mo ago), licensed MIT. It adds 80 tokens to every session and 1,703 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
Migrate
Intakes external content (notes, CLAUDE.md, Cursor rules, Obsidian/Notion/Apple Notes exports), classifies chunks against the LifeOS taxonomy, and commits with provenance after confidence-tiered approval. USE WHEN /migrate, migrate content, import from other LifeOS, bring in old notes, import Cursor rules, import…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
Profile
View, edit, or clear the LifeOS User Model (PRINCIPALIDENTITY.md) — persistent identity context loaded at session startup. Three intents: View, Edit (identity, goals, constraints, preferences), Clear (reset). Read by Algorithm OBSERVE and skills for personalization. USE WHEN profile, show profile, view profile, who am…
wiki-dashboard
Create dynamic, queryable Obsidian dashboard views using Bases or Dataview. Use for auto-updating tables, indexes, or structured views of vault content; not for ordinary question answering.
session-compact
AI DevKit · Compact a historical AI coding session with Jev when context is long, work is handed off or resumed, or durable continuation facts and memory candidates need extraction.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.