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.
curl -O https://raw.githubusercontent.com/danikf/tik4net/master/.claude/skills/wiki-cleanup/SKILL.mdgit clone --depth 1 https://github.com/danikf/tik4netWrote 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/danikf/tik4net/wiki-cleanup)<a href="https://agentmods.dev/skills/danikf/tik4net/wiki-cleanup"><img src="https://agentmods.dev/badge/skills/danikf/tik4net/wiki-cleanup.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 | $0.00174 | $0.06596 |
| Opus 5 | $0.00087 | $0.03298 |
| Sonnet 5 | $0.00035 | $0.01319 |
| Haiku 4.5 | $0.00017 | $0.00660 |
Grade A, and why
wiki-cleanup 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 6d 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 — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki cleanup
The wiki is the end-user documentation — humans, not agents. It lives in a separate git repository
cloned next to the main repo (../tik4net.wiki, also present in tik4net.sln under the wiki folder).
For the repository's own agent-facing docs, use the project-docs-cleanup skill instead; the two do not
overlap and neither should copy the other.
What the wiki is for
Two readers, and the wiki has to serve both:
- A newcomer who has never used tik4net. They must reach a running program in a couple of minutes, and they must not be made to care about M2 handler keys, EC-SRP5 or transport capability flags to get there. The main way we lose this reader is complexity presented too early.
- A returning reader hunting one technical detail — which transport supports
listen, whatSavesends on an unchanged entity, how a duration is parsed. They need the depth to exist and to be findable.
These pull against each other, and the resolution is ordering, not deletion. Depth is welcome; depth above the basics is the defect. A page is not improved by throwing away what the second reader came for — it is improved by putting it after what the first reader needs.
The page contract
Every page should read in this order. Missing pieces and out-of-order pieces are both findings.
- H1 title, then one to three sentences: what this is and when you would use it. A page that opens mid-thought ("Second option is to use…") fails here — it only makes sense to someone who arrived from one specific link.
- Status banner, only if the subject is alpha/experimental. One line, once per page.
- The smallest complete example that works. Copy-paste-runnable, with the
usingdirectives. - The body — what most readers of this page need.
- Details, edge cases, per-transport quirks, internals, performance notes — at the end, under their own heading, or moved behind a link.
- See also — the neighbouring pages.
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.
- 6d ago First seen · 433 lines · 174 tokens per session scan A 856fb5bab6f5
wiki-cleanup is a skill published in the GitHub repository danikf/tik4net (197 stars, last pushed 2d ago), licensed Apache-2.0. It adds 174 tokens to every session and 6,596 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
generate-code-cs
Generate the code from typespec for C#. Parameter: C# SDK repository root location .
translate-a-sample
Translate the Azure SDK sample from python to C# and generate markdownn file for the sample. Parameters: C# SDK repository root; python SDK repository root; Package name: one of Azure.AI.Projects, Azure.AI.Projects.Agents or Azure.AI.Extensions.OpenAI; The name of sample file in Python SDK repository.
build-sample-matrix
Build the matrix of all the samples throughout different frameworks.
author-test
Generate a test given sample. Parameters: C# SDK repository root; Package name: one of Azure.AI.Projects, Azure.AI.Projects.Agents or Azure.AI.Extensions.OpenAI; the sample to use as a starting point for the test.
update-changelog
Update the CHANGELOG.md files of C# projects. Parameters: csroot C# SDK repository root.
budget-checker
Validates that a proposed trip fits within the user's stated budget.