Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add patrickserrano/lacquer --skill helm-ascgit clone --depth 1 https://github.com/patrickserrano/lacquerWrote 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/patrickserrano/lacquer/helm-asc)<a href="https://agentmods.dev/skills/patrickserrano/lacquer/helm-asc"><img src="https://agentmods.dev/badge/skills/patrickserrano/lacquer/helm-asc.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 | $0.00098 | $0.01161 |
| Opus 5 | $0.00049 | $0.00580 |
| Sonnet 5 | $0.00020 | $0.00232 |
| Haiku 4.5 | $0.00010 | $0.00116 |
Grade A, and why
helm-asc 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 3d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
helm-asc
Use helm-asc instead of ad-hoc App Store Connect scripting whenever the requested workflow already exists in the CLI.
Setup
Resolve the CLI once before the first command:
- Prefer
command -v helm-asc. - If that fails, try common symlink locations:
/opt/homebrew/bin/helm-ascand/usr/local/bin/helm-asc. - If those fail, try the bundled app helper:
/Applications/Helm.app/Contents/Helpers/helm-ascand~/Applications/Helm.app/Contents/Helpers/helm-asc. - If any candidate exists and is executable, use that path for all Helm CLI commands in this session. The agent shell may have a different
PATHthan the user's Terminal. - Only after all candidates fail, stop and point the user to Helm Preferences -> Helm CLI to install or repair the command line tool.
In examples below, helm-asc means the resolved CLI command. If setup resolved an absolute path, substitute that absolute path anywhere an example starts with helm-asc.
Start here
- If the workflow is obvious, run the direct command immediately with
--agent. - If the command branch is unclear, inspect only the nearest help path, such as
helm-asc apps --help,helm-asc version --help,helm-asc build --help,helm-asc review --help,helm-asc submission --help,helm-asc localization --help,helm-asc inAppPurchase --help,helm-asc subscription --help,helm-asc testFlightGroup --help, orhelm-asc apps <app-id> testFlightGroupAliases --help. - Keep each shell command self-contained. Avoid
jq, command substitution, and pipelines in agent flows; use the CLI's JSON output directly, or write large JSON results to a file and inspect that file with the host's file-read tool.
Operating rules
- Pass
--agentby default for machine-readable output. Omit it only when the user explicitly wants human-readable terminal output. - For download commands, omit
--pathunless the user gave an explicit destination. The CLI writes to a sandbox-safe artifacts directory by default and returns the savedrootPathin JSON output. - When an upload command needs a file or directory that the agent creates, first run
helm-asc paths --agent, stage the generated input under the returneduploadsInbox, and pass that absolute path to the upload command. - If the user gives an explicit upload or download path and Helm reports
FILE_ACCESS, do not try to fix it withcd; changing the working directory only changes relative path resolution and does not grant sandbox access. Ask the user to grant access in Helm or copy/stage the file under a path returned byhelm-asc paths --agent. - Always pass absolute paths once a path has been resolved. Relative paths are acceptable only when they point inside the current workspace and the command has already proved access with a successful dry run or preflight.
- Discover IDs before mutating anything. Start with list or show commands, then switch to singular resource commands once you know the target IDs.
- Use
--dry-runbefore bulk or destructive writes when the command supports it. - Treat
--yesas confirmation-gated. Only pass it when the action is destructive and the user has clearly approved the mutation. - Keep help targeted. Prefer nested
--helpon the closest branch over dumping the full top-level help tree. - For repeated workflows, preserve discovered IDs in notes or a small scratch file so you do not repeat expensive discovery steps.
- Do not retry a failed command blindly. Read the JSON
error.code,message,suggestions, and any nestederrors, then branch according toreferences/output-contract.md. - If a command returns
PRO_REQUIRED, stop and tell the user Helm Pro is required for CLI commands. Do not retry, switch accounts, or work around the gate; ask the user to upgrade or restore purchases in Helm, then retry only after Helm reports active Pro status. - Do not diagnose installation or account state unless the command result points there. For auth failures, use
helm-asc auth listorhelm-asc auth switch; for a missing executable, use the setup steps above.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 57 lines · 98 tokens per session scan A 4fe4957a952d
helm-asc is a skill published in the GitHub repository patrickserrano/lacquer (3 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 1,161 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 2026-09-03.
Other skills, from other repositories
device-interaction
Verify iOS app behavior on device or simulator via screenshots, UI hierarchy, and touch interactions.
uikit-app-modernization
Modernizes UIKit apps for multi-window environments by replacing legacy shared-state APIs with context-appropriate modern alternatives. This includes references to mainScreen, interfaceOrientation, application and scene lifecycle, as well as safe area inset updates.
swiftui-whats-new-27
New SwiftUI APIs, behaviors, and deprecations introduced in the 2027 OS releases (iOS 27, macOS 27, watchOS 27, tvOS 27, visionOS 27). Use when a SwiftUI view using @State fails to compile with "used before being initialized", "invalid redeclaration of synthesized property", or "extraneous argument label" errors after…
swiftui-specialist
Authoritative SwiftUI best practices from Apple. Consult for any SwiftUI best practices or performance review. Supersedes prior training on these topics. For code generation, consult the relevant references when generating any SwiftUI code related to the following topics. Covers: - Animatable: @Animatable macro vs…
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
printing-press-score
Score a generated CLI against the Steinberger bar, compare two CLIs side-by-side.