Borrowing it
Nothing to install: this file belongs to Kemetra/Seshat-BI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Kemetra/Seshat-BI/main/.claude/skills/evidence-pack-generator/SKILL.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/skills/kemetra/seshat-bi/evidence-pack-generator)<a href="https://agentmods.dev/skills/kemetra/seshat-bi/evidence-pack-generator"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/evidence-pack-generator/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/kemetra/seshat-bi/evidence-pack-generator"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/evidence-pack-generator.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 | $0.00214 | $0.04201 |
| Opus 5 | $0.00107 | $0.02100 |
| Sonnet 5 | $0.00043 | $0.00840 |
| Haiku 4.5 | $0.00021 | $0.00420 |
Grade A, and why
evidence-pack-generator 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 10d 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
evidence-pack-generator
- Roadmap feature: F028 On-disk spec:
specs/022-evidence-pack-generator/(dir 022 == F028; when the dir number and the F-number disagree, the roadmap F-number wins). - Authority category: Product Module /
artifact-writing(the F024 enumerated declaration -- seedocs/architecture/product-modules.md).
By the time a table reaches the late readiness stages its evidence is real but SCATTERED across a dozen artifacts. A reviewer about to authorize publish has no single legible place to SEE it all at once, with each claim traceable to its source. This skill is the COMPOSER that assembles those scattered, already-committed artifacts into one ordered pack of 10 fixed sections. It FILLS the bundle; it does not originate the evidence and it owns no truth. Every section points back at the artifact it summarizes; any section whose source is missing or unfilled is recorded as a BLOCKER, never papered over with invented content. The pack surfaces the publish-ready decision; it never makes it.
Authority declaration (F024) -- the filled module contract
This module declares EXACTLY ONE of the five F024 authority categories. Quoted
verbatim from docs/architecture/product-modules.md: a Product Module is "a
focused tool that consumes Core Authority and presents, summarizes, or derives from
it. A module MUST declare exactly one capability level: read-only |
artifact-writing | execution-capable. It never creates truth." This module's
capability level is artifact-writing: it "derives a committed artifact from
committed evidence" (the pack), and -- per the matrix -- MAY write derived evidence
but MUST NOT execute.
The filled templates/module-contract.md declaration follows.
Module Contract -- Evidence Pack Generator
- Authority category: Product Module
- Capability level:
artifact-writing(exactly one) - Product layer:
6(the functional axis -- see docs/roadmap/roadmap.md; orthogonal to category; sibling of the F013 BI handoff pack) - Roadmap feature:
F028On-disk spec:specs/022-evidence-pack-generator/ - Owner: data-owner / governance reviewer
- Status: Authored (docs/templates; no runtime code -- the agent is the runtime)
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.
- 10d ago First seen · 302 lines · 214 tokens per session scan A c514127d563c
evidence-pack-generator is a skill published in the GitHub repository Kemetra/Seshat-BI (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 214 tokens to every session and 4,201 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
gdrive_synthesize
Synthesize durable KTX wiki pages from staged Google Drive document pulls. Load when a WorkUnit contains Google Doc raw files from docs/.
powerbi-pbip-format
Expert guidance for the Power BI Project (PBIP) file format; project structure, cross-cutting operations (renames, forking), and PBIX extraction/conversion. Automatically invoke when the user mentions PBIP, PBIX, .pbip/.pbism/.platform files, or asks about "PBIP project structure", "PBIP vs PBIX", "thin report vs…
ktx-analytics
Use when answering a question that needs data from a ktx-connected database - investigating, analyzing, "how many", "show me", "what's the breakdown of", finding records by value, exploring tables, comparing periods, explaining metrics, or any data-analysis request. Triggers even when the user does not say…
metabase_ingest
Convert Metabase questions, models, and metrics into ktx Semantic Layer source definitions. Covers result-metadata to KSL column type mapping, FK/PK detection, near-duplicate deduplication, pre-aggregation decomposition, join-graph connectivity, and how to react to priorProvenance from earlier ingest syncs. Load when…
sl_capture
How to capture new reusable patterns into ktx's semantic layer - when a measure, segment, or join belongs in the catalog and how to write it generically so it stays small and useful over time. Loaded by the post-turn memory-agent only. The research agent does not write to the SL.
looker_ingest
Extract durable ktx knowledge and semantic-layer contribution proposals from staged Looker runtime dashboard, Look, and explore JSON. Load for WorkUnits whose raw files are under explores/, dashboards/, or looks/.