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 davekilleen/Dex --skill diff-adoptgit clone --depth 1 https://github.com/davekilleen/DexWrote 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/davekilleen/dex/diff-adopt)<a href="https://agentmods.dev/skills/davekilleen/dex/diff-adopt"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/diff-adopt/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/davekilleen/dex/diff-adopt"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/diff-adopt.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 | $0.00067 | $0.03022 |
| Opus 5.5 | $0.00027 | $0.01209 |
| Sonnet 5.5 | $0.00013 | $0.00604 |
| Haiku 4.5 | $0.00007 | $0.00302 |
Grade A, and why
diff-adopt 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 1mo 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 — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What This Command Does
In plain English: Someone figured out a great way to use Dex for a specific job — like prepping for meetings, reviewing deals, or building performance evidence. This command reads their methodology and walks you through setting up a similar workflow in your vault. It adapts to your role, your tools, and your folder structure. Nothing is copied from their system — your Dex generates everything fresh, tailored to you.
When to use it:
- Dex suggested a workflow you might like
- You found a workflow on heydex.ai/diff
- Someone shared a methodology URL or file path with you
How to run it:
/diff-adopt @davekilleen/meeting-intelligence
/diff-adopt https://heydex.ai/diff/davekilleen/meeting-intelligence
/diff-adopt 04-Projects/DexDiff/beta/diffs/meeting-prep.yaml
Arguments
$ARGUMENTS - A reference to one methodology document:
- A hosted reference
@<handle>/<diff-id>- fetch the raw methodology from the API host:GET https://api.heydex.ai/api/diff?author=<handle>&id=<diff-id> - A page URL like
https://heydex.ai/diff/<handle>/<diff-id>- parse out the handle and diff id, then make the same API call. Never WebFetch the page itself: heydex.ai pages are a React app shell and contain no methodology text. The API lives onapi.heydex.ai; the website host has no/api/*routes. - A local path from the DexDiff draft area, usually under
DEXDIFF_DIFFS_DIR(default04-Projects/DexDiff/beta/diffs/meeting-prep.yaml) (read directly)
The argument is always an explicit location — never a bare name.
Fetch failures must stop the flow with a plain explanation, never silently:
- HTTP 404 - "That workflow was not found. Check the handle and workflow id - the author may have unpublished it."
- Network failure - "Could not reach api.heydex.ai - check your connection and try again. Nothing was changed."
- The response should be a full methodology document carrying
dexdiff_schema: "2.0". If it is a short one-line summary instead, say so plainly: "This workflow was published in an old thin format that cannot be regenerated faithfully - ask the author to re-publish it." Do not invent the missing methodology.
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.
- 1mo ago First seen · 352 lines · 67 tokens per session scan A 7caeb1a0c29b
diff-adopt is a skill published in the GitHub repository davekilleen/Dex (508 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 3,022 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 2026-09-03.
Other skills, from other repositories
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
meeting-notes
Use when the user asks to capture, structure, or summarize meeting notes / call notes / 1:1 discussion / standup notes. Produces a standard template with attendees, agenda, decisions, action items (owner + deadline), and open questions.
schedule
Reminders, automations, and recurring page, dashboard, or status monitoring (cron, RRULE, or fire-at).
inbox-management
Ongoing Gmail inbox management via scheduled runs. Archives known noise, flags urgent items, drafts replies in-thread (never auto-sends), and catches stale follow-ups. Empty polls spend no model tokens. Starts in flag-only mode.
inbox-cleanup
Run a high-recall, multi-pass email inbox cleanup. Pattern-based subject queries catch 25x more archivable email than sender scans alone. Includes urgency triage, classification signals, and post-cleanup filter setup.
notifications
Send notifications through the unified notification router.