A build helper for macOS applications that runs the repository's build command and reports whether the server and client apps succeeded. It can also launch the server app when requested.

Use it to build the two macOS apps, inspect their build results, report errors and sizes, and optionally open the server app.

It turns build output into a concise success, failure, error, and app-size report. It also points out a documented SDK and linker issue when that specific build failure occurs.

How r0shi/harborclerk configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to r0shi/harborclerk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/r0shi/harborclerk/main/.claude/skills/build-macos/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/r0shi/harborclerk

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/r0shi/harborclerk/build-macos/github.svg)](https://agentmods.dev/skills/r0shi/harborclerk/build-macos)

Your own site

<a href="https://agentmods.dev/skills/r0shi/harborclerk/build-macos"><img src="https://agentmods.dev/badge/skills/r0shi/harborclerk/build-macos/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/r0shi/harborclerk/build-macos"><img src="https://agentmods.dev/badge/skills/r0shi/harborclerk/build-macos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 354 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00028	$0.00354
Opus 5.5	$0.00011	$0.00142
Sonnet 5.5	$0.00006	$0.00071
Haiku 4.5	$0.00003	$0.00035

Measured 21d ago against content hash 0a30e976f323, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

build-macos 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 21d 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.

.claude/skills/build-macos/SKILL.md · 31 lines

What it actually says

Build macOS Apps

Run make apps in macos/ to build both macOS apps. Parse the output for build success/failure and report a summary. All paths are relative to the repository root.

Steps

Run (cd macos && make apps 2>&1)
Check output for BUILD SUCCEEDED or BUILD FAILED / error: lines
Report:
- Whether each app (HarborClerkServer, HarborClerk) built successfully
- Any build errors (show the actual error lines)
- App sizes from the "Server app" / "Client app" lines
- The ==> Version line: package.sh derives it from git describe (scripts/build-version.sh), so an untagged commit builds as <last tag> (<commits since>) and a dirty tree adds .dirty to the stamp. Report it as printed; never "fix" it in the pbxproj (see docs/releasing.md).
If the user said "and run" or "and launch", open the server app: open macos/build/output/HarborClerkServer.app

If the build stops at configure: error: C compiler cannot create executables, the Command Line Tools SDK is newer than Xcode's linker; see the SDKROOT note in macos/AGENTS.md. Signing (make sign) is never run by an agent.

Changes

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.

21d ago Changed · +5 lines 0a30e976f323
1mo ago First seen · 26 lines · 28 tokens per session scan A 2eaa241e08ee

Subscribe to this mod's changes

build-macos is a skill published in the GitHub repository r0shi/harborclerk (3 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 354 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-17.

Debugging LLM docker document-intelligence hybrid-search local-first macos

build-macos next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
build-macosr0shi/harborclerk	Skill	3	2d ago	MIT	A	28	Claude Code
alert-sopPM-Shawn/Abu-Cowork	Skill	419	3d ago	Apache-2.0	A	20	Claude Code
code-reviewAlex8791-cyber/cognithor	Skill	156	4d ago	Apache-2.0	A	13	Claude Code, Codex
gini-bug-reportOpen-Curiosity/gini-agent	Skill	2.3k	3mo ago	MIT	A	47	Claude Code
memobasemaximskorohod/memobase	Skill	22	17d ago	MIT	A	25	Claude Code, Codex
systematic-debuggingtaracodlabs/aiden	Skill	873	18d ago	AGPL-3.0	A	15	Claude Code, Codex
network-diagnosticstaracodlabs/aiden	Skill	873	18d ago	AGPL-3.0	A	21	Claude Code, Codex

harborclerk: Skill for Claude Code