tik4net: Skill for Claude Code

.claude/skills/pre-release-check/SKILL.md

pre-release-check is a skill for Claude Code from danikf/tik4net. It costs 145 tokens per session (5,740 once invoked), scanned A, original, Apache-2.0.

A release-readiness review for the tik4net library, checking automated gates and issues that require human judgement before tagging a version.

In plain words
What is it for?
Use it before alpha, beta, release-candidate, or stable releases to run checks, review version markers, and decide whether shipping is appropriate.
Why use it?
A passing command is not enough if it did not really test anything, and release problems can affect every project that depends on the library.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is danikf/tik4net's own configuration. It tells Claude Code how to work on tik4net 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 tik4net configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is grep -n "(planned)" README.md ../tik4net.wiki/Home.md.

Reuse

Borrowing it

Nothing to install: this file belongs to danikf/tik4net. 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/danikf/tik4net/master/.claude/skills/pre-release-check/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/danikf/tik4net

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 pre-release-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/danikf/tik4net/pre-release-check/github.svg)](https://agentmods.dev/skills/danikf/tik4net/pre-release-check)
Your own site
<a href="https://agentmods.dev/skills/danikf/tik4net/pre-release-check"><img src="https://agentmods.dev/badge/skills/danikf/tik4net/pre-release-check/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 pre-release-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/danikf/tik4net/pre-release-check"><img src="https://agentmods.dev/badge/skills/danikf/tik4net/pre-release-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,740 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00145 $0.05740
Opus 5.5 $0.00058 $0.02296
Sonnet 5.5 $0.00029 $0.01148
Haiku 4.5 $0.00015 $0.00574

Measured yesterday against content hash b92f6fd9160e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pre-release-check 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 yesterday.

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/pre-release-check/SKILL.md · 414 lines

How it starts

The opening of the file, as written. The whole thing — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-release check

A release is the moment the library stops being ours and starts being somebody's dependency. This skill is the list of things worth knowing before that, split by whether a machine can decide them.

Two rules govern everything below.

A check that could not have failed has measured nothing. Before believing a green result, ask what outcome would have been red. This is not paranoia — it is how a whole class of green runs turn out to be runs that never executed. See the traps section; each entry there is a real one from this repository.

Severity is about the user, not about the finding. A wrong answer the caller cannot detect outranks a crash, which outranks anything cosmetic. A library that silently returns different data on a Czech machine is worse than one that throws.

The two lanes

Keep them apart. Mixing them is how a release checklist becomes a wall nobody reads.

Gates Reviews
Decided by a command, deterministically judgement
Failure means do not tag write it down, then decide
Where they live CI where possible, this skill otherwise this skill, usually delegated to an agent

Run the gates first — they are cheap and they can invalidate the reviews.


Part 1 — Gates

1.0 Is the version ready?

A version is ready when its key features are done and no bug is open — measured by exactly that, not by how long it has been in development or how much else landed.

  • Key features: the version's list under What's new in README.md (mirrored on the wiki's Home). Every bullet ships and works; none still says (planned). A feature that will not make it is moved to the next version's list, not left planned in a tagged one.
  • No open bug: nothing open in the version's todo (the maintainer's local release notes — ask for them), and no open GitHub issue labelled as a bug against it. A known defect is fixed or explicitly moved out with the maintainer's decision, never shipped unmentioned.

Read the full file on GitHub · 414 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. yesterday Changed b92f6fd9160e
  2. 19d ago Changed · +47 lines 51c85f8fa1e6
  3. 1mo ago Changed · +17 lines 3ef8eac84548
  4. 1mo ago Changed · +6 lines f350e8e72aca
  5. 2mo ago First seen · 344 lines · 145 tokens per session scan A 067a52a9cea5

Subscribe to this mod's changes

pre-release-check is a skill published in the GitHub repository danikf/tik4net (198 stars, last pushed yesterday), licensed Apache-2.0. It adds 145 tokens to every session and 5,740 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-30.