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 Syniox5334/apple-dev-skills --skill apple-dash-docsetsgit clone --depth 1 https://github.com/Syniox5334/apple-dev-skillsWrote 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/syniox5334/apple-dev-skills/apple-dash-docsets)<a href="https://agentmods.dev/skills/syniox5334/apple-dev-skills/apple-dash-docsets"><img src="https://agentmods.dev/badge/skills/syniox5334/apple-dev-skills/apple-dash-docsets/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/skills/syniox5334/apple-dev-skills/apple-dash-docsets"><img src="https://agentmods.dev/badge/skills/syniox5334/apple-dev-skills/apple-dash-docsets.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 | $0.00041 | $0.01208 |
| Opus 5.5 | $0.00016 | $0.00483 |
| Sonnet 5.5 | $0.00008 | $0.00242 |
| Haiku 4.5 | $0.00004 | $0.00121 |
Grade A, and why
apple-dash-docsets 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 2mo 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Dash Docsets
Purpose
Manage Dash docsets and cheatsheets on macOS with one top-level entry point. scripts/run_workflow.py is the authoritative runtime path for stage selection, fallback order, source priority, approval gating, and structured generation guidance; it does not replace the agent's own Dash access methods.
When To Use
- Use this skill for Dash search and discovery requests.
- Use this skill for Dash installation requests after search has identified a missing docset.
- Use this skill for Dash generation guidance when installation cannot complete.
- Use this skill when the user needs the exact fallback path between agent-side Dash MCP usage, local HTTP, and URL or Service integration.
- Recommend
apple-xcode-workflowwhen the user needs Apple or Swift execution, diagnostics, build or test work, or Apple docs reasoning outside Dash management. - Recommend
apple-swift-package-bootstrapwhen the user is starting a brand new Swift package rather than managing Dash content.
Single-Path Workflow
- Classify the request into one stage:
searchinstallgenerate
- If no stage is explicit, start at
search. - Run
scripts/run_workflow.pywith the selected stage:search: applies configured fallback order and returns a structured access-path decisioninstall: applies configured source priority and approval gatinggenerate: returns structured automation-first guidance
- If the selected stage cannot complete, hand off forward through
references/stage-handoff-contract.md:search -> installinstall -> generate
- Return one status, one
path_type, and one output contract for the stage that ran.
Inputs
stage:search,install, orgeneratequery: required forsearchdocset_identifiers: optional forsearch; use installed identifiers onlydocset_request: required forinstallandgenerateapproval: required before side-effectful install actions- Defaults:
- runtime entrypoint:
python3 scripts/run_workflow.py searchaccess order ismcp -> http -> url-service- install source priority is
built-in,user-contributed,cheatsheet - default search result limit is
20 - default search snippets setting is
true
- runtime entrypoint:
What ships with it
19 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.
- agents/openai.yaml 316 B
- references/automation-prompts.md 3.3 KB
- references/catalog_built_in_docsets.json 33 KB
- references/catalog_cheatsheets.json 30 KB
- references/catalog_user_contrib_docsets.json 142 KB
- references/customization-flow.md 2.4 KB
- references/customization.template.yaml 322 B
- references/dash_http_api.md 1.2 KB
- references/dash_mcp_tools.md 1.2 KB
- references/dash_url_and_service.md 1.0 KB
- references/snippets/apple-swift-core.md 2.3 KB
- references/stage-handoff-contract.md 684 B
- scripts/customization_config.py 6.1 KB runs code
- scripts/dash_api_probe.py 2.4 KB runs code
- scripts/dash_catalog_match.py 3.0 KB runs code
- scripts/dash_catalog_refresh.py 5.3 KB runs code
- scripts/dash_url_install.py 1.6 KB runs code
- scripts/dash_url_search.py 1.0 KB runs code
- scripts/run_workflow.py 9.9 KB runs code
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.
- 2mo ago First seen · 121 lines · 41 tokens per session scan A 61833316f651
apple-dash-docsets is a skill published in the GitHub repository Syniox5334/apple-dev-skills (5 stars, last pushed 25d ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,208 once invoked, about $0.0002 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 2026-08-31.
apple-dash-docsets compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| apple-dash-docsetsSyniox5334/apple-dev-skills | Skill | 5 | 25d ago | Apache-2.0 | A | 41 | Codex |
| deconstruct-bias-dialogue0xagi-bsky-social/Codex-Skills | Skill | 2 | 5mo ago | MIT | A | 99 | Codex |
| hr-onboardingnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 62 | Claude Code, Codex |
| book-mirrorgarrytan/gbrain | Skill | 32k | today | MIT | A | 138 | Claude Code |
| exam-forecastanthropics/claude-for-legal | Skill | 9.9k | today | Apache-2.0 | A | 73 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | yesterday | MIT | A | 81 | Claude Code |
| deck-course-modulenexu-io/html-anything | Skill | 9.4k | yesterday | Apache-2.0 | A | 25 | Claude Code, Codex |