agentmods.dev

velocity.report: Skill for Claude Code

.claude/skills/docs-release-prep/SKILL.md

docs-release-prep is a skill for Claude Code from banshee-data/velocity.report. It costs 46 tokens per session (3,304 once invoked), scanned C, original, Apache-2.0.

A documentation release-preparation workflow for checking and organising Markdown files. Markdown is plain text with simple formatting used for many project documents.

In plain words
What is it for?
Use it to verify links, update completed plans, split large documents, simplify long specifications, record decisions, and check documentation included in a disk image.
Why use it?
It catches broken links, outdated design records, unresolved questions, oversized files, and incomplete release documentation before the files are shipped.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument.

This is banshee-data/velocity.report's own configuration. It tells Claude Code how to work on velocity.report 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 velocity.report configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/check-relative-links.py --report 2>&1.

not rated 11repo changed 9d ago C scan 46 tokens original Apache-2.0
View source ↗ banshee-data/velocity.report velocity.report
Reuse

Borrowing it

Nothing to install: this file belongs to banshee-data/velocity.report. 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/banshee-data/velocity.report/main/.claude/skills/docs-release-prep/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/banshee-data/velocity.report

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 docs-release-prep

README.md
[![agentmods](https://agentmods.dev/badge/skills/banshee-data/velocity.report/docs-release-prep/github.svg)](https://agentmods.dev/skills/banshee-data/velocity.report/docs-release-prep)
Your own site
<a href="https://agentmods.dev/skills/banshee-data/velocity.report/docs-release-prep"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/docs-release-prep/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.

agentmods 80×15 button for docs-release-prep

Your own site · 80×15
<a href="https://agentmods.dev/skills/banshee-data/velocity.report/docs-release-prep"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/docs-release-prep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,304 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00046 $0.03304
Opus 5.5 $0.00018 $0.01322
Sonnet 5.5 $0.00009 $0.00661
Haiku 4.5 $0.00005 $0.00330

Measured 9d ago against content hash ea7b2824fc08, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

docs-release-prep scanned grade C with 1 finding 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 9d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

(`[label](path)`), not a standalone backtick-quoted file path. <!-- link-ignore -->
.claude/skills/docs-release-prep/SKILL.md · 395 lines

How it starts

The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: docs-release-prep

Run the full documentation preparedness workflow before a release. This skill codifies the sequence of editorial and structural checks that make docs accurate, navigable, and sized for purpose.

Usage

/docs-release-prep
/docs-release-prep --dry-run
/docs-release-prep --scope lidar

Goals

  1. Every Markdown link resolves to a real file.
  2. Key document references use Markdown links, not backtick-quoted file paths.
  3. Every completed plan is graduated (symlink + hub-doc consolidation).
  4. No spec document exceeds the length target without justification.
  5. Large documents with distinct topics are split into focused files.
  6. Open design questions are surfaced; answered questions are recorded.
  7. Design decision tables reflect current implementation, not stale drafts.
  8. Documentation included in the disk image is complete and correct.

Rubrics

Length target: 800 lines

Specification and architecture documents should target ≤ 800 lines. This is a guideline, not a hard wall: a 900-line doc with dense tables is fine; a 2,000-line doc that wanders is not.

No compilable code blocks

Plan files and design documents must not contain fenced code blocks in compilable languages. See STYLE.md § Documentation Structure for the full banned/allowed lists. The short version:

Banned: Go, SQL, Protocol Buffers, TypeScript, Swift, Python, JSON, JSONC, YAML, TOML, XML, CSV, HTML, CSS, Typst, Makefile, Dockerfile.

Allowed: bash/sh (operational commands), mermaid (diagrams), text (ASCII art, directory trees).

Replace banned blocks with prose descriptions, field tables (| Field | Type | Purpose |), or file references. Keep the information; change the format.

Split threshold

If a document covers two or more clearly independent topics and exceeds 800 lines, split it:

  1. Extract the secondary topic into a new file in the same directory.
  2. Add a cross-reference link from the original to the new file.
  3. Keep the original as the primary document for the core topic.

Read the full file on GitHub · 395 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. 9d ago Changed · +9 lines ea7b2824fc08
  2. 1mo ago First seen · 386 lines · 46 tokens per session scan C 989201916747

Subscribe to this mod's changes

docs-release-prep is a skill published in the GitHub repository banshee-data/velocity.report (11 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 3,304 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-25.

DocumentsWriting and docslidarradarroad-safetystreet-safetytraffic-analysisurban-analytics
Related

docs-release-prep compared with skills from other repositories

docs-release-prep next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
docs-release-prepbanshee-data/velocity.reportSkill11todayApache-2.0C46Claude Code
orbit-notionnexu-io/open-designSkill106kyesterdayApache-2.0A117Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-pluginsSkill35k2d agoApache-2.0A123Claude Code
apify-youtube-transcript-scrapersickn33/agentic-awesome-skillsSkill49kyesterdayMITA48Claude Code
legal-holdanthropics/claude-for-legalSkill9.9k3d agoApache-2.0A68Claude Code
ppt-reviewOrkas-AI/OrkasSkill9.0kyesterdayMITA2Claude Code, Codex
readtw93/WazaSkill7.5k4d agoMITA61Claude Code