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 exmergo/dex --skill maintaingit clone --depth 1 https://github.com/exmergo/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/exmergo/dex/maintain)<a href="https://agentmods.dev/skills/exmergo/dex/maintain"><img src="https://agentmods.dev/badge/skills/exmergo/dex/maintain/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/exmergo/dex/maintain"><img src="https://agentmods.dev/badge/skills/exmergo/dex/maintain.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 | $0.00235 | $0.03399 |
| Opus 5.5 | $0.00094 | $0.01360 |
| Sonnet 5.5 | $0.00047 | $0.00680 |
| Haiku 4.5 | $0.00023 | $0.00340 |
Grade A, and why
maintain 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 yesterday.
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.
Maintain
Keep the repository correct as the world underneath it moves, on both of its
axes: the dbt project and the semantic layer. Drift is measured against a
baseline, the .dex/snapshot.json fingerprint of the warehouse map and of
each project layer. Detection is read-only; only reconcile proposes edits, and
transform apply is the one door that writes them.
Procedure
dex works in one loop: explore, transform, maintain. Every step runs one engine command, reads the single JSON envelope it prints, and decides the next step from that envelope.
- Explore before you write. Before writing or fixing SQL against a table
whose columns, types, grain, or join keys you have not verified in this
session, run
explore map(orexplore profile <tables>for a few named ones) and read its grain, keys, PII flags, and data-quality findings. Answer ad-hoc questions withexplore query, never with a raw database client. - Plan the change. Author the file content and hand it to
transform plan(orsemantic define|update|planfor the semantic layer). Nothing is written yet. Read the diffs, thewarnings, and, on a model that already exists,data.row_attribution; re-plan until they describe the change you meant. - Apply it.
transform apply <plan-id>writes the plan as a reviewable git diff. A human edit made since planning comes back asneeds_confirmation: re-plan against the current files. - Build and verify on dev. Run
transform build --target dev --verify. Readdata.verification.ranfirst, then relay the findings and anything undersuppressed. A green build says dbt ran, not that the rows are right. - Maintain.
maintain checkcompares the warehouse and the project with the.dex/snapshot.jsonbaseline, andmaintain verifychecks the project as it is now with no baseline.maintain reconcileproposes the fix as a plan, applied withtransform apply. Takemaintain snapshotafter a known-good build.
What ships with it
3 files 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.
- yesterday Changed a9d21172ce6d
- 2d ago Changed · +10 lines f6dedf41cb56
- 4d ago Changed · +22 lines · +2 tokens per session dfa1236df832
- 6d ago Changed · +5 lines · -103 tokens per session 528c22d96696
- 8d ago Changed · +12 lines ce64cbf722a8
- 9d ago Changed · +1 lines scan C → A 7531d632b112
- 12d ago Changed · -97 lines b3e5a6602a2f
- 1mo ago Changed · +2 lines 202ffe442367
- 1mo ago Changed · +44 lines f74d44745b64
- 1mo ago First seen · 229 lines · 336 tokens per session scan C 18a71c068d9c
maintain is a skill published in the GitHub repository exmergo/dex (88 stars, last pushed today), licensed Apache-2.0. It adds 235 tokens to every session and 3,399 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
data-engineer
Use when designing database schemas, writing complex SQL queries, building ETL pipelines, or optimizing data transformations — with validation at every step.
backend-architect
Use when implementing server-side logic, designing middleware, integrating databases, or building API endpoints — with TDD and verification discipline.
sql_optimizer
Skill "sql_optimizer" from G-Schumacher44/strata-oss, covering skill: sqloptimizer, trigger, inputs, allowed tools and forbidden.
sql_builder
Skill "sql_builder" from G-Schumacher44/strata-oss, covering skill: sqlbuilder, trigger, inputs, allowed tools and forbidden.
bq_schema_probe
Skill "bq_schema_probe" from G-Schumacher44/strata-oss, covering skill: bqschemaprobe, trigger, inputs, allowed tools and forbidden.
bq_query_guardrail
Skill "bq_query_guardrail" from G-Schumacher44/strata-oss, covering skill: bqqueryguardrail, trigger, inputs, allowed tools and forbidden.