Borrowing it
Nothing to install: this file belongs to ilia3546/swift-argument-parser-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/ilia3546/swift-argument-parser-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/ilia3546/swift-argument-parser-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/instructions/ilia3546/swift-argument-parser-mcp/claude-md)<a href="https://agentmods.dev/instructions/ilia3546/swift-argument-parser-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ilia3546/swift-argument-parser-mcp/claude-md/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.
<a href="https://agentmods.dev/instructions/ilia3546/swift-argument-parser-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ilia3546/swift-argument-parser-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01268 | $0.01268 |
| Opus 5 | $0.00634 | $0.00634 |
| Sonnet 5 | $0.00254 | $0.00254 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
swift-argument-parser-mcp CLAUDE.md 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 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.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Pointer file for Claude Code and other AI agents working on this repository.
Stop.
CONTRIBUTING.mdis the single source of truth for code style, MARK policy, documentation policy, testing expectations, branch/commit/PR conventions, the "adding a new feature" checklist, and the "things not to do" list. Past sessions have shipped work that violated it because the agent skipped this step — don't be that session.
Mandatory pre-flight (every task, before any edit)
- Read
CONTRIBUTING.mdin full. Every section applies to AI agents. Memory of a previous session is not a substitute — the file changes. - If the task touches a
publicsymbol, also openSources/ArgumentParserMCP/Documentation.docc/ArgumentParserMCP.mdand decide upfront whether## Topicsand an article underDocumentation.docc/Articles/need to change. - For anything non-trivial, work the Checklist: adding a new feature end-to-end and tick every box before reporting the task as done.
Rules that get missed most often
Restated here because past sessions have ignored them. The authoritative
wording still lives in CONTRIBUTING.md — when in doubt, that file wins.
- Branch names —
<type>/<short-slug>where<type>is one offeature,fix,perf,refactor,docs,test,chore,ci,build. Don't invent new prefixes (noclaude/,agent/,wip/). If the harness created a branch with a non-conforming prefix, flag it to the user before pushing instead of silently using it. - PR titles —
<type>: <imperative subject>using the same type set, with the matching label applied so the change lands in the right section of the auto-generated release notes (see.github/release.yml). Append!after the type for breaking changes. Useskip-changelogfor PRs that shouldn't appear in the changelog at all. - Commit subjects — imperative, ≤72 chars, no Conventional-Commits
prefix on the commit itself (
feat:/fix:lives on the PR title, not on commits). One logical change per commit. If a hook fails, make a new commit — never amend a commit that didn't land. - Code style — 4-space indent, K&R braces, 120-col line limit,
///docs on every newpublic/internalsymbol, imports sorted withFoundationfirst, trailing commas in multi-line collections,letovervar,finalon classes. No force operations inSources/(!,try!,as!) — don't relax this to make a tricky conversion compile, surface the type problem instead. - Comments — by default, write none. Only add a comment when the why is non-obvious (workaround, hidden invariant, external constraint). Don't narrate what the code does.
- MARK policy — files longer than ~200 lines must use the canonical
section order from
CONTRIBUTING.md. Don't introduce a new long file without sectioning it. - Doc surface split — DocC is user-facing only; process, style, and
internal architecture stays in
CONTRIBUTING.md. The README is a pitch + quickstart and only changes when existing info became inaccurate or the new capability is pitch-worthy. - Testing — every new public function needs at least one happy-path and
one failure / edge-case test. End-to-end behaviour goes through
MCPProcessClientinMCPServerIntegrationTests.swift. - Tooling —
swift build/swift testis the entire local toolchain by design. Don't propose Makefiles, helper scripts, or lint configuration on your own.
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.
- 9d ago First seen · 95 lines · 1,268 tokens per session scan A 808b319e9612
swift-argument-parser-mcp CLAUDE.md is an instructions file published in the GitHub repository ilia3546/swift-argument-parser-mcp (7 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,268 tokens to every session, about $0.0063 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.