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 kriscard/Skills --skill spot-driftgit clone --depth 1 https://github.com/kriscard/SkillsWrote 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/kriscard/skills/spot-drift)<a href="https://agentmods.dev/skills/kriscard/skills/spot-drift"><img src="https://agentmods.dev/badge/skills/kriscard/skills/spot-drift.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 | $0.00067 | $0.01406 |
| Opus 5 | $0.00034 | $0.00703 |
| Sonnet 5 | $0.00013 | $0.00281 |
| Haiku 4.5 | $0.00007 | $0.00141 |
Grade A, and why
spot-drift 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 8d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spot Drift
Compare stated intentions against actual vault behavior over the past 30 days. Surface the gap between what you say matters and where energy actually goes. Find what's being avoided.
Ask, Don't Assume
Shared principle (canonical version in the vault skill): never guess, deduce, or fill gaps with
assumptions about the user's notes, priorities, or intent. If you don't know — a date range, what
counts as a win, which goals are active — ask. Before writing any synthesis or judgment into a
note, show your draft with its source and get explicit confirmation. Missing data is not permission
to invent.
Obsidian Access
Use Obsidian CLI via Bash. On failure: "Obsidian CLI isn't working — update Obsidian with CLI enabled."
Step 1 — Gather Stated Intentions
OKRs and Goals
obsidian files folder="2 - Areas/Goals/Quaterly/" format=json
obsidian files folder="2 - Areas/Goals/Monthly/" format=json
# Read the most recent quarterly and monthly goal notes
obsidian base:query path="2 - Areas/Goals/OKR Dashboard.base" format=json
Extract: stated priorities, self-commitments, items marked important/urgent, open questions flagged for investigation, projects in active/current status.
Daily Note Intentions (past 30 days)
TODAY="2 - Areas/Daily Ops/$(date +%Y)/$(date +%Y-%m-%d).md" # then read backwards
obsidian read path="2 - Areas/Daily Ops/<year-from-YYYY-MM-DD>/YYYY-MM-DD.md"
obsidian property:read path="2 - Areas/Daily Ops/<year-from-YYYY-MM-DD>/YYYY-MM-DD.md" name="energy_sleep"
Completion: attempt all 30 dates, list missing or sparse notes explicitly, and do not treat gaps as proof of inactivity.
Look for: "I need to..." / "I should..." / "I want to..." statements, carry-forward items from reflections, recurring themes that keep appearing, things flagged as tomorrow's priority that never get done.
Step 2 — Gather Actual Behavior
Vault Activity per Stated Priority
obsidian search:context query="<stated priority A>" format=json limit=10
obsidian search:context query="<stated priority B>" format=json limit=10
obsidian backlinks file="<priority project note>" counts
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.
- 8d ago First seen · 149 lines · 67 tokens per session scan A 5487c790309b
spot-drift is a skill published in the GitHub repository kriscard/Skills (14 stars, last pushed 27d ago), licensed MIT. It adds 67 tokens to every session and 1,406 once invoked, about $0.0003 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
done
Summarize the current agent session, create an Obsidian note for it, and link it from today's daily note. Use when the user is finished with a session and wants to log what was accomplished.
weekly-review
Summarize the past week's daily notes, extracting key findings, links, action items, and potential atomic notes, and write the summary into the matching weekly note.
skillsmith
Discover, install, compare, and manage Claude Code skills. Search the registry, get recommendations, validate skill quality, and manage your installed skills.
organize-inbox
Move notes from the Inbox to their respective folders based on their frontmatter category.
daily-rhythm
Automated daily planning and reflection system with morning briefs, wind-down prompts, sleep nudges, and weekly reviews. Use when the user wants to set up a structured daily routine, morning briefings, evening reflection prompts, or weekly planning sessions. Triggers include requests for daily schedules, morning…
getajob
AI-powered job search assistant. Scan job listings, track applications, maintain dream company lists, and generate tailored resumes and cover letters. Use when the user wants to find jobs, run a job scan, set up job search, track applications, or prepare application materials.