help

help is a command for coding agents from Kemetra/Seshat-BI. It costs 15 tokens per session (661 once invoked), scanned A, original, Apache-2.0.

Show the installed Seshat BI command map and how each surface is used.

Command

Install

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.

agentmods
npx agentmods add commands/kemetra/seshat-bi/help
Clone the repo
git clone --depth 1 https://github.com/Kemetra/Seshat-BI

Wrote 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.

agentmods badge for help

README.md
[![agentmods](https://agentmods.dev/badge/commands/kemetra/seshat-bi/help.svg)](https://agentmods.dev/commands/kemetra/seshat-bi/help)
Your own site
<a href="https://agentmods.dev/commands/kemetra/seshat-bi/help"><img src="https://agentmods.dev/badge/commands/kemetra/seshat-bi/help.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 661 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00015 $0.00661
Opus 5 $0.00008 $0.00331
Sonnet 5 $0.00003 $0.00132
Haiku 4.5 $0.00002 $0.00066

Measured today against content hash 27cf6b752471, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

help 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 today.

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.

distribution/bundle-templates/claude/commands/help.md · 49 lines

What it actually says

Report the installed Seshat BI surface truthfully; never advertise anything absent from this list.

Slash commands (Claude Code namespaces them by plugin, so invoke as /seshat-bi:<name>, e.g. /seshat-bi:next):

  • help -- this command map.
  • init -- initialize or inspect a fresh project safely.
  • check -- run and interpret the static governance check.
  • status -- report the truthful per-table readiness status.
  • next -- return the one truthful next readiness action.
  • doctor -- run and interpret the workspace health check.
  • review -- review readiness evidence and stop at the human gate.
  • auto -- run the governed autonomous loop until the next human gate.
  • dbt-doctor -- check governed dbt prerequisites without a database query.
  • dbt-plan -- validate Mapping Ready and prepare an immutable execution plan.
  • dbt-build -- execute the fixed shadow graph under an accepted plan digest.
  • dbt-review -- review normalized dbt evidence and stop at the human gate.
  • powerbi-design -- guarded dashboard/page design from approved metric contracts.
  • powerbi-review -- screenshot review, dashboard QA, blueprint validation, PBIR review.
  • powerbi-theme -- theme JSON, palette, typography, filter-pane defaults, backgrounds, canvas.
  • powerbi-format -- formatting plans and governed PBIR formatting/geometry.
  • powerbi-adopt -- adopt an existing PBIP project through assess/scaffold.
  • dagster-doctor -- read-only orchestration preflight (environment, pinned dagster, gates).
  • dagster-run -- execute one governed orchestration job, fail-closed behind every gate.
  • dagster-evidence -- list runs or render a run's committed derived evidence.

The former names seshat-init, seshat-check, seshat-next, and seshat-review remain as deprecated aliases for one release cycle and behave identically to their bare forms.

Bundled skills: seshat-bi (readiness router), dbt-workflows (governed dbt routing), powerbi-workflows (guarded Power BI routing), and the knowledge skills bi-sql-knowledge, bi-dax-knowledge, bi-python-knowledge, bi-bigdata-knowledge, and retail-kpi-knowledge.

Slash commands and terminal CLI verbs are different surfaces: a slash command is a reviewed prompt inside this agent session, while seshat is a separately installed Python package (pipx install seshat-bi). If seshat is not installed, say so instead of simulating its output. Useful CLI-only verbs with no slash wrapper include validate, drift, semantic-check, generate, value-check, evidence-pack, approvals, pack, and watch; list everything with seshat --help.

Changes

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.

  1. today First seen · 49 lines · 15 tokens per session scan A 27cf6b752471

Subscribe to this mod's changes

help is a command published in the GitHub repository Kemetra/Seshat-BI (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 15 tokens to every session and 661 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.