Seshat-BI: Skill for Claude Code

.claude/skills/release-notes-generator/SKILL.md

release-notes-generator is a skill for Claude Code from Kemetra/Seshat-BI. It costs 237 tokens per session (4,824 once invoked), scanned A, original, Apache-2.0.

A release-note drafting and maturity-checking guide for the Seshat BI project. It records what a shipped roadmap change makes possible and rates that capability only against available evidence.

In plain words
What is it for?
Use it to draft the required sections of a release note, assess the honest maturity of a new capability, and document what became possible in a release.
Why use it?
It prevents release notes from relying only on commit messages and prevents early examples from being overstated as production-ready. It also makes the project’s progress easier to review later.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is Kemetra/Seshat-BI's own configuration. It tells Claude Code how to work on Seshat-BI itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Seshat-BI configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Kemetra/Seshat-BI/main/.claude/skills/release-notes-generator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Kemetra/Seshat-BI

Made for: Claude Code.

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 release-notes-generator

README.md
[![agentmods](https://agentmods.dev/badge/skills/kemetra/seshat-bi/release-notes-generator.svg)](https://agentmods.dev/skills/kemetra/seshat-bi/release-notes-generator)
Your own site
<a href="https://agentmods.dev/skills/kemetra/seshat-bi/release-notes-generator"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/release-notes-generator.svg" alt="Measured on agentmods" height="20"></a>
Per session 237 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,824 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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 5.1 $0.00237 $0.04824
Opus 5 $0.00118 $0.02412
Sonnet 5 $0.00047 $0.00965
Haiku 4.5 $0.00024 $0.00482

Measured 8d ago against content hash 0021fb3a6545, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

release-notes-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 8d 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.

.claude/skills/release-notes-generator/SKILL.md · 304 lines

How it starts

The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.

release-notes-generator

  • Roadmap feature: F033 On-disk spec: specs/027-release-maturity-management/ (dir 027 == F033; when the dir number and the F-number disagree, the roadmap F-number wins).
  • Authority category: Maintenance Automation (the F024 enumerated declaration -- see docs/architecture/product-modules.md). NO connectivity level and NO capability level: those sub-axes belong to Execution Adapters and Product Modules; Maintenance Automation carries neither (its boundary is prose).

The kit ships in slices. Each slice changes WHAT THE KIT CAN DO, but the kit has no durable, reviewable record of "what became possible in this release, and how mature is the capability". Today that answer lives only in commit messages and the roadmap's delivered ledger. This skill is the record: it DRAFTS a per-release note (seven required blocks) and ASSESSES an evidence-gated maturity ladder. It composes evidence others already recorded; it originates none of it and owns no truth. A maturity claim is exactly where a tool is tempted to round "two worked examples" up to "production ready"; the kit's no-fake-confidence rule (hard rule #9) forbids that, so the ladder is an evidence-gated MILESTONE ladder -- not a score -- and the skill drafts-and-stops for a named release owner to approve.

Authority declaration (F024) -- Maintenance Automation (no sub-axis)

This skill declares EXACTLY ONE of the five F024 authority categories. Quoted verbatim from docs/architecture/product-modules.md, Maintenance Automation is:

a tool that runs WITHOUT a per-invocation human trigger (scheduled / CI), emits ONLY derived evidence (a report, a drift signal, a recomputed index), never creates truth, and never self-approves. This is the novel category: it is distinguished from a human-invoked Module by the absence of a per-run human trigger. The schedule itself -- and the evidence it runs on -- is a prior named-human action, so this does NOT relax Principle V.

Read the full file on GitHub · 304 lines

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. 8d ago First seen · 304 lines · 237 tokens per session scan A 0021fb3a6545

Subscribe to this mod's changes

release-notes-generator is a skill published in the GitHub repository Kemetra/Seshat-BI (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 237 tokens to every session and 4,824 once invoked, about $0.0012 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.