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 agentmods add instructions/kemetra/seshat-bi/agents-mdgit 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/instructions/kemetra/seshat-bi/agents-md)<a href="https://agentmods.dev/instructions/kemetra/seshat-bi/agents-md"><img src="https://agentmods.dev/badge/instructions/kemetra/seshat-bi/agents-md.svg" alt="Measured on agentmods" 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 | $0.01759 | $0.01759 |
| Opus 5 | $0.00879 | $0.00879 |
| Sonnet 5 | $0.00352 | $0.00352 |
| Haiku 4.5 | $0.00176 | $0.00176 |
Grade A, and why
Seshat-BI AGENTS.md 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 2d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md -- operating rules for agents in this repo
Seshat BI is agent-first: you (the agent) are the interface; the CLI
gates (seshat check, retail validate) are helpers you CALL, never the product.
This file is the short operating contract. The full law is
.specify/memory/constitution.md; the spine is docs/readiness/readiness-model.md.
Naming. The product is Seshat BI (package alias
Seshat_BI). It was previously developed under the internal name Tower BI Agent Kit; the governance spine is still the Readiness System. Same product, one brand.
Decide from readiness state
- Read the table's readiness status (
templates/readiness-status.yamlshape) to findcurrent_stageandnext_action. Launch the workflow for THAT stage only -- never skip ahead. - The seven stages, in order: Source -> Mapping -> Silver -> Gold -> Semantic
Model -> Dashboard -> Publish. A stage is entered only when the prior is
pass. - The
retail-orchestrateconductor sequences the verbs; the readiness status records the state. Recomputecurrent_stagefrom committed artifacts +Gate status+ migration presence -- there is no separate run-state engine.
Hard stops (never cross these)
- Do NOT proceed to silver when
mapping_readyisblocked(orGate statusis notCLEARED). Nosilver.*SQL before an approved map (Principle IV). - Do NOT point Power BI at gold before
retail validatepasses (Principle VIII). - Do NOT design dashboards before metric contracts exist (roadmap rule 5).
- Do NOT run the Power BI execution adapter on your own initiative (the official
Power BI MCP / connection;
pbi-clino longer the preferred path) -- feature 016, gated onsemantic_model_ready(Principle II). It is EXECUTION-ONLY (it cannot define metrics, mappings, semantic logic, or dashboard design), and no readiness stage depends on it. Since ADR 0018 (ratified 2026-08-18) the LOCAL slice ships:seshat pbi-mcp plan-write/applyrun only against a target and operation RESOLVED from the committed allowlist, never free-form, and only when the owner asks for that write. The REMOTE slice remains deferred and owner-gated. Reaching for either unasked is still a hard stop -- a shipped verb is not a standing authorization. - Do NOT self-grant an approval. Approvals are named human actions (Principle V): grain, PII publish-safety, business rollups, sentinel-vs-null.
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.
- 2d ago First seen · 117 lines · 1,759 tokens per session scan A faa1e0026a8a
Seshat-BI AGENTS.md is an instructions file published in the GitHub repository Kemetra/Seshat-BI (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,759 tokens to every session, about $0.0088 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 instructions, from other repositories
ktx AGENTS.md
AGENTS.md instructions for Kaelio/ktx, covering ktx development notes, critical rules, absolute requirements, absolute prohibitions and language convention.
tuva-core AGENTS.md
AGENTS.md instructions for tuva-health/tuva-core, covering tuva core agent operating manual, tuva core 1.0 contract, repository boundaries, architecture and public-contract rules and extension columns.
docglow CLAUDE.md
Instructions for docglow/docglow, covering claude.md — docglow, project, tech stack, build & test and python.
dbt-doctor AGENTS.md
Instructions for northgraindata/dbt-doctor, covering dbt-doctor, stack, commands and conventions.
sidemantic AGENTS.md
AGENTS.md instructions for sidequery/sidemantic, covering sidemantic, usage preference (important), codebase structure, version management and validation before commits.
sidemantic CLAUDE.md
Claude Code instructions for sidequery/sidemantic, a project described as: The universal metrics layer. Compatible with 15+ formats: Cube, MetricFlow, LookML, Omni, BSL, LDM, Cortex, Malloy, OSI, SML, TML, Hex, Rill, Superset.