Borrowing it
Nothing to install: this file belongs to sysprog21/zhtw-mcp. 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/sysprog21/zhtw-mcp/main/.claude/skills/zhtw-conventions/SKILL.mdgit clone --depth 1 https://github.com/sysprog21/zhtw-mcpWrote 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/sysprog21/zhtw-mcp/zhtw-conventions)<a href="https://agentmods.dev/skills/sysprog21/zhtw-mcp/zhtw-conventions"><img src="https://agentmods.dev/badge/skills/sysprog21/zhtw-mcp/zhtw-conventions.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00108 | $0.01558 |
| Opus 5 | $0.00054 | $0.00779 |
| Sonnet 5 | $0.00022 | $0.00312 |
| Haiku 4.5 | $0.00011 | $0.00156 |
Grade A, and why
zhtw-conventions 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 2d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zhtw-mcp conventions
The gate settles formatting and correctness. cargo fmt, clippy, black,
shellcheck and scripts/indent.sh run in make check, so none of that is
here. What is here is what a reviewer would otherwise have to say out loud,
plus the rules enforced by the git hooks rather than by CI: the commit message
and the staged-content checks. Any cargo build installs them, through
build.rs; make hooks installs them on their own.
README.md and CLAUDE.md are the tracked and local halves respectively, and
this file does not restate either. Where two of them speak to the same thing,
README.md wins.
Commit messages
The house style is Chris Beams' seven rules, and scripts/git-commit-msg.sh
enforces the mechanical ones: subject within 50 columns, capitalized,
imperative, no trailing period, no backticks, no conventional-commit type
prefix, body wrapped at 72 columns, no em dash character, no tabs, and no
control or bidirectional-override characters. An area prefix such as
Windows: retry the replace is not a conventional-commit prefix and is
allowed. Run
git log --no-merges --format=%s if you want the calibration set rather than
the claim; the log sits at 43 columns in the median.
Two of those rules are this project's rather than Beams'. Widths are counted in
terminal columns, so a CJK character costs two, which is what
git log --oneline has to fit. And the subject line is English prose that may
quote a Chinese term, which is what every subject in this log already is:
Narrow 聯繫 cross_strait flagging to contact-copy
Add word "test" to negative_context_clues for pass rule
Take the binary under test from cargo
The rule the hook cannot check is what the body says. This tree keeps its detailed reasoning in the comment next to the code, often several paragraphs per decision. A body that retells the mechanics duplicates that comment and then goes stale on its own. Write the premise and the trade, once, usually a single paragraph. Backticks are fine there and not in the subject.
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.
- 2d ago First seen · 128 lines · 108 tokens per session scan A f9c5e2846639
zhtw-conventions is a skill published in the GitHub repository sysprog21/zhtw-mcp (475 stars, last pushed today), licensed MIT. It adds 108 tokens to every session and 1,558 once invoked, about $0.0005 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 2026-09-05.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
git-commit
Creates git commits following Conventional Commits format with type/scope/subject and detailed markdown body. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md. Each change type gets its own markdown heading (# emoji + type), with…
levelup-publish
Compile accepted Context Directive Records (CDRs) into team-ai-directives artifacts and create a draft PR. Builds context modules, evals goldensets, and/or skills based on CDR context types.