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 resetgit 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/reset)<a href="https://agentmods.dev/skills/davekilleen/dex/reset"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/reset/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/reset"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/reset.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 | $0.00098 | $0.01436 |
| Opus 5.5 | $0.00039 | $0.00574 |
| Sonnet 5.5 | $0.00020 | $0.00287 |
| Haiku 4.5 | $0.00010 | $0.00144 |
Grade A, and why
reset 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reset Dex for changed answers
If 04-Projects/ does not exist, this vault was never set up. Use setup instead.
If the user actually changed jobs or roles — new employer, new email domain, an
old identity to archive — use change-job instead: it runs this same reset and
then guides the passes a reset alone never touches (re-sorting people for the
new domain, archiving old-role goals, priorities and projects, re-pointing open
tasks). A reset by itself is the right lever only for changed preferences or
answers within the same working life.
To turn a single room on or off, use manage-capabilities — it is a much smaller
change than a full reset and never touches the rest of the profile.
Otherwise:
-
Tell the user what a reset does and does not do, and get an explicit yes before calling anything:
"I'll walk you through the same questions as first-time setup and rewrite your profile — role, company, pillars, communication style, working week and rooms. Every setting you don't re-answer carries forward unchanged, and nothing you've written is deleted or moved: your notes, people, meetings and projects all stay exactly where they are. Want to go ahead?"
Stop here if they decline.
-
Call
start_onboarding_session(force_new=True)fromonboarding-mcp. Theforce_newflag is what makes this a reset rather than resuming a half-finished setup. Know what it re-arms: the fresh session clears the calendar answer and the harness confirmation, so the flow's calendar step and harness-selection confirmation must both be replayed —finalize_onboardingrefuses to run until each has been addressed again. Do not skip past them expecting the old answers to still count. -
Read
.claude/flows/onboarding.mdand follow it as the single source of the conversation, exactly assetupdoes. -
Before finalizing, call
finalize_onboarding(dry_run=True)and show the user what it reports it would create, plus theprofile_changeslist — every profile setting that will change, old value → new value. Settings not in that list carry forward. Tell the user that on a vault that already completed onboarding, finalizing first takes a snapshot of the current profile, pillars and room choices — before anything is rewritten — so the reset can be checked afterwards and undone if it went wrong. Then callfinalize_onboarding(). -
After finalizing, show the user the
transition_verificationsummary from the finalize response — it reads "Changed (you chose): … Carried forward: N settings. Lost: none." Read it before relaying it: if it reports anything lost or changed outside their answers, say so plainly instead of declaring success, and offerrestore_transition_capsule— preview first (it defaults to a dry run), then rerun it withdry_run=falseif they want the two settings files put back exactly as they were.verify_transitionre-runs the same check anytime against the snapshot named in the response.
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 Changed c4dd8c42e416
- 1mo ago Changed · +39 lines · +31 tokens per session f63b05ec5a06
- 1mo ago First seen · 69 lines · 67 tokens per session scan A ffd03be604ce
reset is a skill published in the GitHub repository davekilleen/Dex (508 stars, last pushed 2d ago), licensed MIT. It adds 98 tokens to every session and 1,436 once invoked, about $0.0004 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
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
vellum-memory-v3-migration
One-time migration of an existing memory-v2 concept corpus into the memory-v3 section-grain "wiki" — topical articles with a stand-alone lead and queryable sections — with loss-proof staging, assistant-reviewed authoring, and a retrieval-eval gate before cutover.
vellum-memory-v2-migration
Perform a one-time migration from memory v1, to memory v2, which was introduced in 0.8.0.
daily-briefing
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…
ha-knowledge
Working method for the Hope Agent knowledge space — how to capture, organize, link, retrieve, and maintain Markdown notes well with the note tools. Load whenever you are reading or writing notes in an attached knowledge base. Trigger on: user asks to take / save / organize / restructure notes, build or grow a…
catchup
Restore context after /clear by summarizing recent work and project state.