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.
git clone --depth 1 https://github.com/Kemetra/Seshat-BIWrote 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/commands/kemetra/seshat-bi/dagster-run)<a href="https://agentmods.dev/commands/kemetra/seshat-bi/dagster-run"><img src="https://agentmods.dev/badge/commands/kemetra/seshat-bi/dagster-run/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/commands/kemetra/seshat-bi/dagster-run"><img src="https://agentmods.dev/badge/commands/kemetra/seshat-bi/dagster-run.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 | $0.00013 | $0.00352 |
| Opus 5 | $0.00006 | $0.00176 |
| Sonnet 5 | $0.00003 | $0.00070 |
| Haiku 4.5 | $0.00001 | $0.00035 |
Grade A, and why
dagster-run 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 6d 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.
What it actually says
Load the dagster-workflows skill. Run
seshat dagster run --job <full_sequence_job|through_gold_job> (add
--table <table> to scope one mapped table) and interpret the result. Choose
the Bronze source with --source-mode: the default csv lands a raw
<table>.csv and OWNS/reloads bronze.<table>; existing-bronze is the
non-destructive DB-first mode -- it verifies an already-loaded bronze.<table>
READ-ONLY (zero Bronze writes) and starts the gated tail from there. Use
existing-bronze when Bronze already lives in the warehouse (loaded by BCP,
COPY, an external ETL, or a prior tool) and must not be dropped or reloaded;
never export Bronze back to a CSV just to feed the default path. The run
executes ONLY already-approved steps behind every gate: a failed gate halts all
downstream assets and the command exits 3 -- report that as the honest
fail-closed signal with the recorded blocking reason and named owner, never as
something to bypass. The mapping gate, semantic-model approval, and
publish_ready are READ from committed artifacts; never edit them to make a run
green (approval is a named human's action). Run evidence is rendered to
orchestration/dagster/run-evidence/<run-id>.md; cite it. Without database
credentials the DB-touching assets record a deferred boundary -- say so
truthfully. A green run is evidence, never a readiness pass.
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.
- 6d ago First seen · 24 lines · 13 tokens per session scan A 22049a7eb20e
dagster-run is a command published in the GitHub repository Kemetra/Seshat-BI (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 13 tokens to every session and 352 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
migrating-fabric-trial-capacities
Migrate workspaces from trial capacity to production capacity.
rclone_serve_http
Serve the remote over HTTP.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.