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-generategit 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-generate)<a href="https://agentmods.dev/skills/davekilleen/dex/diff-generate"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/diff-generate/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-generate"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/diff-generate.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 | $0.00070 | $0.01321 |
| Opus 5.5 | $0.00028 | $0.00528 |
| Sonnet 5.5 | $0.00014 | $0.00264 |
| Haiku 4.5 | $0.00007 | $0.00132 |
Grade A, and why
diff-generate 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What This Command Does
In plain English: You've built a workflow in Dex that works well. This command scans your vault, identifies what you've customised, and writes a methodology document describing how it works. That document can be published to heydex.ai/diff so others can adopt a similar setup using /diff-adopt.
When to use it:
- You want to share a workflow with someone else
- You want to document how a part of your system works
- You want to package your setup for your team
How to run it:
/diff-generate "my meeting prep workflow"
/diff-generate
Arguments
$ARGUMENTS: Optional description of the workflow to package.
- If provided: used to identify which components belong to this workflow
- If omitted: scans everything custom and asks what to package
Process
Step 1: Discover Customisations
Scan these locations for custom components:
.claude/skills/ - custom or modified skills
.claude/hooks/ - custom hooks
CLAUDE.md - custom sections
.claude/CLAUDE.md - local extensions
To identify what's custom vs. baseline dex-core:
- Skills with
-customsuffix are always custom - Skills with
-daveor other personal suffixes are custom - Hooks are almost always custom
- CLAUDE.md sections that reference specific folders, people, or workflows are custom
Present findings:
I found these customisations in your vault:
Skills ([count] custom):
[skill-name] - [one-line description]
...
Hooks ([count]):
[hook-name] - [one-line description]
...
CLAUDE.md extensions ([count] custom sections detected)
What would you like to package?
- Describe a workflow (e.g. "my meeting prep")
- Or pick from the list above
Step 2: Group into a Workflow
If the user provided a description, use it to identify related components.
Grouping heuristic: components belong together if:
- They serve the same job to be done (meeting prep, deal review, weekly planning)
- Skills reference the same vault paths
- A hook fires on output from a skill in the same group
- A CLAUDE.md section describes when to use skills in the group
- Skills are typically run in sequence
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 156 lines · 70 tokens per session scan A 19e47a3d4573
diff-generate is a skill published in the GitHub repository davekilleen/Dex (508 stars, last pushed 3d ago), licensed MIT. It adds 70 tokens to every session and 1,321 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
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.
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
schedule
Reminders, automations, and recurring page, dashboard, or status monitoring (cron, RRULE, or fire-at).
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.
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.
notifications
Send notifications through the unified notification router.