Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    CLAUDE.md & AGENTS.md Pruner + Skill Trigger Check

    1

    Flags wrong and dead lines in CLAUDE.md/AGENTS.md/Cursor rules by file:line, checks them against the repo, then checks SKILL.md triggers.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    CLAUDE.md & AGENTS.md Pruner + Skill Trigger Check

    CLAUDE.md & AGENTS.md Pruner + Skill Trigger Check

    Example session with this skill installed

    [REAL public repo, run for this test: github.com/Dimillian/IceCubesApp at commit 98098b9c; rule files last changed in d8e46d28]
    User: "Our CLAUDE.md and AGENTS.MD are 277 lines. Prune them and tell me what's wrong."
    Script run: python3 agent-rules-pruner/scripts/lint.py /workspace/oss/IceCubesApp
    Also checked by hand: ls Packages/, test target names in Packages/*/Package.swift, .swiftformat, AlternateIcons/, Packages/AppAccount/.../AppAccountsManager.swift, and a search of the Swift sources for getHomeTimeline.

    • Read your context and instructions
    • Compiled the claude md

    Agent rules audit - IceCubesApp (98098b9c)

    Summary: one 277-line CLAUDE.md (~2,274 tokens by the linter's rough count). AGENTS.MD is a symlink to it (commit 0513b2e8), so both names already point at the same text. It can become

    one 25-line file (~374 tokens), with the symlink kept. The 3 fixes that matter: a test scheme that doesn't exist (NetworkTests), a hard-coded /Users/thomas/... project path, and a package list that's missing four packages and names one wrong.

    Wrong or stale (fix first)

    File:lineSaysRepo actually hasFix
    CLAUDE.md:28test_sim scheme: "NetworkTests"Test target is NetworkClientTests (Packages/NetworkClient/Package.swift)Rename. An agent running this gets a "scheme not found" error
    CLAUDE.md:26-305 test schemesAlso StatusKitTests existsAdd it, since StatusKit is where the post editor lives
    CLAUDE.md:14, 23projectPath: "/Users/thomas/Documents/Dev/Open Source/IceCubesApp/..."Only valid on one machineUse <repo>/IceCubesApp.xcodeproj or a relative path
    CLAUDE.md:14 vs 174build_sim_name_proj vs build_ios_sim_name_projTwo different tool names for the same job; at most one matches the installed XcodeBuildMCPKeep one (line 14's is used with session defaults). Check against the server's tool list
    CLAUDE.md:39-49Packages: Models, Network, Env, DesignSystem, Account, Timeline, StatusKit, Notifications, MediaUIPackages/ has NetworkClient (not Network) plus AppAccount, Conversations, Explore, ListsReplace with the real list
    CLAUDE.md:39packages under /Packages/Leading slash reads as filesystem rootPackages/
    CLAUDE.md:69"40+ app icons"AlternateIcons/ has 3 entries in this checkout (icons may live in the asset catalog too)Unverified. Drop the number; the agent doesn't need it
    AGENTS.MDsymlink to CLAUDE.md-Fine as is: one file, two names. The linter reports it as a symlink, not a duplicate. Keep it

    Section verdicts

    Section (lines)VerdictWhy
    Title + intro (1-7)Keep, shortenOne line is enough. The heading says "CLAUDE.md", but tools also read this file as AGENTS.MD
    Build / tests (9-31)FixWrong scheme, missing scheme, personal paths
    Formatting (33-34)KeepRepo-specific and checkable
    Package structure (36-49)FixStale list
    Key patterns, legacy (51-58)Keep, merge"No new ViewModels" is the most important rule in the file. It's stated 4 times (52, 81, 255, 273)
    App extensions (60-64)Keep, shortenUseful map, one line
    Implementation details (66-71)CutProduct description (privacy proxy, icons, DeepL), not instructions
    Core philosophy (75-81)Cut"Embrace its declarative nature", "don't fight the framework": not checkable
    State management, ownership (85-98)CutThe model already knows what @State and @Binding are
    TimelineView example (100-137)Move or cutGeneric sample code, not repo code: getHomeTimeline() appears nowhere in the Swift sources. Point to a real view instead
    Async patterns (139-144)MergeKeep "no Combine for new code"; the rest is generic
    Composition, organization (146-158)CutGeneric; line 156 "when appropriate" is uncheckable
    Build verification (160-175)MergeThe rule is good ("build, fix errors, run tests"); the example block duplicates 9-31 with a third command variant and a placeholder path
    Implementation examples (177-241)Cut65 lines of sample code. The AppAccountsManager sketch roughly matches the real class (Packages/AppAccount, @Observable, availableAccounts: [AppAccount]), but the agent can read the real one
    Best practices DO / DON'T (243-261)MergeKeep only line 261 (don't nest @Observable), which is a real, specific pitfall
    Testing strategy (263-269)CutGeneric
    Code style when editing (271-277)Merge"Maintain existing patterns in legacy code" (272) conflicts with "no ViewModels" unless scoped. The proposed file says how

    Proposed file (CLAUDE.md, 25 lines, about 374 tokens by the same rough count)

    Agent instructions

    IceCubesApp: a Mastodon client in SwiftUI for iOS, iPadOS, macOS and visionOS.

    Build and test (XcodeBuildMCP)

    Use the project path of your own checkout.

    mcp__XcodeBuildMCP__session-set-defaults projectPath: "<repo>/IceCubesApp.xcodeproj" simulatorName: "iPhone Air"
    mcp__XcodeBuildMCP__build_sim_name_proj scheme: "IceCubesApp"
    mcp__XcodeBuildMCP__test_sim scheme: "<Package>Tests"
    

    Test schemes: AccountTests, EnvTests, ModelsTests, NetworkClientTests, StatusKitTests, TimelineTests.
    After editing code: build, fix compile errors, and run the tests of any package you changed.

    Formatting: SwiftFormat, 2-space indent, config in .swiftformat.

    Layout

    Swift packages in Packages/: Account, AppAccount, Conversations, DesignSystem, Env, Explore, Lists, MediaUI, Models, NetworkClient (Mastodon, DeepL and OpenAI clients), Notifications, StatusKit, Timeline.
    Extensions: NotificationService (push decryption), Share, Action, Widgets.

    How new code is written

    • No new ViewModels. Views hold their state with @State and a ViewState enum (loading / loaded / error), and load data in .task.
    • Shared services are @Observable and injected with .environment(...). Don't nest @Observable objects inside other @Observable objects; it breaks observation. Create services at the view level.
    • async/await for all API calls; no Combine for new code.
    • Legacy views that already use ViewModels: keep their pattern when making small fixes. Don't half-convert them.

    AGENTS.MD stays a symlink to this file.

    Skill trigger check

    No SKILL.md files in the repo.

    Not checked

    • Which XcodeBuildMCP tool names your installed version exposes (run its tools list)
    • Whether contributors rely on the long examples. If so, move them to docs/swiftui-patterns.md rather than delete
    • The .swiftformat contents (only that the file exists)
    • Whether every tool you use finds AGENTS.MD (upper-case extension) on case-sensitive file systems; the usual name is AGENTS.md
    one 277-line CLAUDE.md

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Checks your CLAUDE.md/AGENTS.md against the actual repo and your SKILL.md triggers in one pass, shown on two real public repos with every finding verified.

    There are good free tools that lint rules files or skill descriptions separately. This one does both in one report, and verifies claims against the code instead of only checking the text.

    • A bundled linter (standard library Python 3.9+, read-only, no network) inventories CLAUDE.md, AGENTS.md, .cursor/rules, copilot-instructions and every SKILL.md. It shows lines and rough tokens, identical files, symlinks, machine-specific /Users/... paths, vague rules, missing referenced paths and repeated lines.
    • It treats audited files as data: lines like curl ... | sh (including bash <(curl ...), iwr ... | iex and commands split across lines), "ignore previous instructions", hidden HTML-comment instructions and invisible Unicode are reported for you to review, never followed.
    • The skill then verifies claims by hand: test schemes and scripts that don't exist, stale package lists, contradictions.
    • Every section gets a verdict (Keep / Fix / Merge / Cut / Move) with a reason, and you get a proposed trimmed file.
    • Skill trigger check: name format, the 1,024-character description limit, the missing "use when..." clause, first-person wording, bodies over ~500 lines, and overlapping skills, with before -> after descriptions.

    Real example: on a public SwiftUI repo (277-line CLAUDE.md, with AGENTS.MD as a symlink to it) it found a test scheme that doesn't exist, a hard-coded personal path and a stale package list, and proposed a 25-line replacement. It's read-only by default and never deletes a rule without saying why.

    Known limitations: the "use when" and first-person checks are regexes, and the security patterns catch common forms only. Treat flags as leads to read, not verdicts.

    Not affiliated with Anthropic, OpenAI, Cursor or GitHub.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Requires manual confirmation for file edits. Cannot verify external API capabilities not documented in the local repo. Symlinks pointing outside the repo are ignored.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 21 days ago

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files
    Listed21 days ago
    Updated7 days ago

    What's inside

    Frequently Asked Questions

    The pruner identifies redundant "generic fluff," stale script references, and machine-specific paths that bloat your context window, directly reducing token costs and preventing the agent from trying to run non-existent commands.

    Yes, it is designed to work with any structured instruction format, including Cursor (.cursorrules, .mdc), GitHub Copilot, CLAUDE.md, and custom SKILL.md files.

    The skill provides a categorized audit (Keep, Fix, Merge, Cut, Move) and recommendations, but it will not modify your local files without your explicit permission and review.

    The package includes the core auditing skill, the `lint.py` script for local inventorying, and a set of templates for optimizing skill trigger descriptions.

    The tool cross-references your instructions against project manifests like `package.json` or `pyproject.toml` to ensure every command referenced in your rules actually exists in your current environment.

    New in Agents & Orchestration