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 agentmods add skills/gaelic-ghost/socket/macos-sandbox-file-access-workflownpx skills add gaelic-ghost/socket --skill macos-sandbox-file-access-workflowgit clone --depth 1 https://github.com/gaelic-ghost/socketWrote 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/gaelic-ghost/socket/macos-sandbox-file-access-workflow)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/macos-sandbox-file-access-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/macos-sandbox-file-access-workflow.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 | $0.00061 | $0.01104 |
| Opus 5 | $0.00030 | $0.00552 |
| Sonnet 5 | $0.00012 | $0.00221 |
| Haiku 4.5 | $0.00006 | $0.00110 |
Grade A, and why
macos-sandbox-file-access-workflow 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 yesterday.
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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
macOS Sandbox File Access Workflow
Purpose
Preserve user intent and access lifetime while selecting the smallest supported file-access mechanism. Treat a URL or path as resource identity, not durable authorization, and keep App Sandbox, TCC, POSIX, and mandatory controls distinct.
When To Use
- Use when a sandboxed Mac app must open, save, import, export, drag, share, or persist access to files or directories.
- Use when access succeeds during selection but fails after relaunch, in a helper, or after a move/rename.
- Use to identify whether a remaining denial is sandbox, TCC, filesystem, volume, coordination, Data Vault, or SIP policy.
Single-Path Workflow
- Record the data owner, exact operation, resource type, read/write/execute need, persistence duration, process boundary, distribution channel, macOS build, and exact error.
- Read
references/sandbox-and-filesystem-control-map.mdand identify every applicable control layer before choosing a capability. - Use the app container or a standard supported container-relative directory when it satisfies the feature. Use an App Group only for a real same-team shared-container requirement.
- Prefer direct user selection through the appropriate open/save panel, document URL, drag/drop, or Photos/File Provider selection surface for external data.
- Request only the user-selected read-only, read-write, or executable entitlement that the feature actually needs. Do not replace a narrow selection with Full Disk Access.
- Create a security-scoped bookmark only when access must survive the current interaction or process lifetime. Follow every step in
references/security-scoped-bookmark-lifecycle.md. - For helpers, XPC services, app extensions, or shared containers, use
references/helpers-groups-and-process-boundaries.md; verify which process resolves and consumes authorization rather than passing a path and assuming authority follows. - Perform the narrow operation and balance every successful
startAccessingSecurityScopedResource()withstopAccessingSecurityScopedResource(). Do not retain access indefinitely for convenience. - If access still fails, classify the exact denying layer: path resolution/symlink, ownership/mode/ACL, sandbox, TCC Files and Folders/Full Disk Access, mount/volume state, coordination, Data Vault, SIP, or service policy.
- Validate relaunch, moved/renamed/removed resources, read-only enforcement, helper/extension behavior, revoked/inaccessible access, stale and malformed bookmark recovery, and privacy-safe logging using
references/validation-fixtures.md.
What ships with it
6 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.
- yesterday First seen · 71 lines · 61 tokens per session scan A 758a4ce64beb
macos-sandbox-file-access-workflow is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 9d ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,104 once invoked, about $0.0003 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
pipeline
Use when the user wants a feature idea taken end-to-end in one autonomous run — phrases like "run the whole pipeline", "take this feature from idea to finished branch", "brainstorm then build it autonomously", "do everything from idea to merged", "implement all phases without stopping". Triggers when they want…
craft
Use when a product idea is still vague and needs to become a clear definition of what to build — "let's craft an app like X", "help me define what I actually want", "clarify this idea before we plan it". Also use before planning or implementation when requirements, UX, domain behaviour, or technical preferences have…
scenario-planning
Plans under genuine uncertainty — building scenarios, identifying which assumptions are load-bearing, setting early-warning indicators, and stress-testing a plan against futures rather than forecasting one. Use this when a decision depends on something unknowable, when a plan assumes conditions that may not hold…
ai-ml-governance
Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…
ai-research-analyst
Produces executive-level research — market sizing, competitor mapping, trend analysis, and strategic intelligence — grounded in cited sources with the confidence in each claim made explicit. Use this to analyze a market or industry, map competitors, evaluate a market-entry or build-versus-buy decision, produce a…
implement-factory
Factory loop orchestrator for multi-feature or multi-component implementation manifests. Use for high-complexity work with parallel-eligible workstreams and holdout-scenario evaluation.